sdp.bib

@inproceedings{MA16a,
title = {TensorFlow: A system for large-scale machine learning},
author  = {Martin Abadi and Paul Barham and Jianmin Chen and Zhifeng  
Chen and Andy Davis and Jeffrey Dean and Matthieu Devin and Sanjay  
Ghemawat and Geoffrey Irving and Michael Isard and Manjunath Kudlur  
and Josh Levenberg and Rajat Monga and Sherry Moore and Derek G.  
Murray and Benoit Steiner and Paul Tucker and Vijay Vasudevan and Pete  
Warden and Martin Wicke and Yuan Yu and Xiaoqiang Zheng},
year  = {2016},
booktitle = {Proceedings of the 12th USENIX Symposium on Operating Systems Design and  
Implementation (OSDI)},
pages = {265--283}
}

@inproceedings{MA16a-short,
title = {TensorFlow: A system for large-scale machine learning},
author  = {Martin Abadi and Paul Barham and Jianmin Chen and Zhifeng  
Chen and Andy Davis and Jeffrey Dean and Matthieu Devin and Sanjay  
Ghemawat and Geoffrey Irving and Michael Isard and Manjunath Kudlur  
and Josh Levenberg and Rajat Monga and Sherry Moore and Derek G.  
Murray and Benoit Steiner and Paul Tucker and Vijay Vasudevan and Pete  
Warden and Martin Wicke and Yuan Yu and Xiaoqiang Zheng},
year  = {2016},
booktitle = {OSDI}
}

@inproceedings{ZA07a,
  title={Personalized ad delivery when ads fatigue: An approximation algorithm},
  author={Abrams, Zo{\"e} and Vee, Erik},
  booktitle={International Workshop on Web and Internet Economics},
  pages={535--540},
  year={2007}
}

@book{YSA12a,
 author = {Abu-Mostafa, Yaser S. and Magdon-Ismail, Malik and Lin, Hsuan-Tien},
 title = {Learning From Data},
 year = {2012},
 publisher = {AMLBook}
} 

@article{DA03a,
 title = {Database-friendly Random Projections: {J}ohnson-{L}indenstrauss
with Binary Coins},
 author = {Achlioptas, Dimitris},
 journal = {Journal of Computer and System Sciences},
 volume = {66},
 pages = {671--687},
 year = {2003}
}

@article{DHA85a,
  title={A learning algorithm for boltzmann machines},
  author={David H. Ackley and Geoffrey E. Hinton and Terrence J. Sejnowski},
  journal={Cognitive science},
  volume={9},
  number={1},
  pages={147--169},
  year={1985}
}

@Article{VA62a,
 title ={An algorithm for the organization of information},
 author={Adelson-Velsky, Georgy Maximovich and Landis, Evgenii Mikhailovich}, 
 journal = {Proceedings of the USSR Academy of Sciences},
 volume={146}, 
 pages = {263--266},
 year = {1962}
}

@ONLINE{ADIDAS13a,
	author = {adidas},
	title = {mi{C}oach {SPEED CELL}},
        howpublished = {\url{http://www.adidas.com}}
}

@inproceedings{AA11a,
 title ={Distributed Delayed Stochastic Optimization},
 author={Alekh Agarwal and John Duchi},
 booktitle = {Advances in Neural Information Processing Systems 24},
 editor = {J. Shawe-Taylor and R.S. Zemel and P. Bartlett and F.C.N. Pereira and K.Q. Weinberger},
 pages = {873--881},
 year = {2011}
}

@misc{AA11c,
  title={Fast global convergence of gradient methods for high-dimensional statistical recovery},
  author={Agarwal, Alekh and Negahban, Sahand N. and Wainwright, Martin J.},
  note={arXiv preprint arXiv:1104.4824},
  year={2011}
}

@article{AA12a,
  author = {Alekh Agarwal and Olivier Chapelle and Miroslav Dudik
and John Langford},
  title  = {A reliable effective terascale linear learning system},
  journal = {Journal of Machine Learning Research},
  year  = {2014},
  volume = {15},
  pages  = {1111--1133}
}

@article{AA12a-short,
  author = {Alekh Agarwal and Olivier Chapelle and Miroslav Dudik
and John Langford},
  title  = {A reliable effective terascale linear learning system},
  journal = {JMLR},
  year  = {2014},
  volume = {15},
  pages  = {1111--1133}
}


@inproceedings{AA19a,
  title={Addressing Trust Bias for Unbiased Learning-to-Rank},
  author={Agarwal, Aman and Wang, Xuanhui and Li, Cheng and Bendersky, Michael and Najork, Marc},
  booktitle={Proceedings of The Web Conference},    
  pages={4--14},
  year={2019}
}

@inproceedings{AA19a-short,
  title={Addressing Trust Bias for Unbiased Learning-to-Rank},
  author={Agarwal, Aman and Wang, Xuanhui and Li, Cheng and Bendersky, Michael and Najork, Marc},
  booktitle={WWW},    
  year={2019}
}

@inproceedings{AA19b,
  title={A General Framework for Counterfactual Learning-to-Rank},
  author={Agarwal, Aman and Takatsu, Kenta and Zaitsev, Ivan and Joachims, Thorsten},
  booktitle={Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval},
  pages={5--14},
  year={2019}
}

@inproceedings{AA19b-short,
  title={A General Framework for Counterfactual Learning-to-Rank},
  author={Agarwal, Aman and Takatsu, Kenta and Zaitsev, Ivan and Joachims, Thorsten},
  booktitle={SIGIR},
  year={2019}
}

@inproceedings{DA14a,
 author = {Agarwal, Deepak and Long, Bo and Traupman, Jonathan and Xin, Doris and Zhang, Liang},
 title = {{LASER}: A Scalable Response Prediction Platform for Online Advertising},
 booktitle = {Proceedings of the 7th ACM International Conference on Web Search and Data Mining (WSDM)},
 year = {2014},
 pages = {173--182}
} 

@inproceedings{DA14b,
 author = {Agarwal, Deepak and Ghosh, Souvik and Wei, Kai and You, Siyu},
 title = {Budget Pacing for Targeted Online Advertisements at {L}inkedIn},
 booktitle = {Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)},
 year = {2014},
 pages = {1613--1619}
} 

@inproceedings{PA23a,
author = {Aggarwal, Pranjal and Deshpande, Ameet and Narasimhan, Karthik},
title = {{S}em{S}up-{XC}: Semantic Supervision for Zero and Few-Shot Extreme Classification},
year = {2023},
booktitle = {Proceedings of the 40th International Conference on Machine Learning}
}

@inproceedings{RA13a,
author = {Agrawal, Rahul and Gupta, Archit and Prabhu, Yashoteja and Varma, Manik},
title = {Multi-Label Learning with Millions of Labels: Recommending Advertiser Bid Phrases for Web Pages},
year = {2013},
booktitle = {Proceedings of the 22nd International Conference on World Wide Web (WWW)},
pages = {13--24}
}

@Book{AA90a,
  author =       {Agresti, Alan},
  title =        {Categorical Data Analysis},
  publisher =    {Wiley},
  year =         {1990},
  address =      {New York}
}


@techreport{IA06a,
author={Ian Anderson and Henk Muller},
institution={Department of Computer Science, University of Bristol},
number={CSTR-06-016},
title={Practical Activity Recognition using {GSM} Data},
pages={8},
month={July},
year={2006},
}

@article{AA11b,
 author={Airola, Antti and Pahikkala, Tapio and Salakoski, Tapio},
 title={Training Linear Ranking {SVM}s in Linearithmic Time Using Red--black Trees},
 journal={Pattern Recognition Letters},
 volume={32},
 number={9},
 pages={1328--1336},
 year={2011},
 publisher={Elsevier}
}

@article{AA11b-short,
 author={Airola, Antti and Pahikkala, Tapio and Salakoski, Tapio},
 title={Training Linear Ranking {SVM}s in Linearithmic Time Using Red--black Trees},
 journal={PR Letters},
 volume={32},
 number={9},
 pages={1328--1336},
 year={2011},
 publisher={Elsevier}
}


@article{JA76,
author      = {John Aitchison and Colin B. Begg},
journal     = {Biometrika},
pages       = {1--12},
title       = {Statistical diagnosis when basic cases are not classified 
               with certainty},
volume      = {63},
year        = {1976}
}

@article{MAA84,
author      = {M. A. Ajiz and A. Jennings},
journal     = {Int. J. Num. Meth. Eng.},
pages       = {949--966},
title       = {A robust incomplete {C}holesky-conjugate gradient algorithm},
volume      = {20},
year        = {1984}
}

@article{ZA13a,
  title={Good practice in large-scale learning for image classification},
  author={Akata, Zeynep and Perronnin, Florent and Harchaoui, Zaid and Schmid, Cordelia},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  volume={36},
  number={3},
  pages={507--520},
  year={2013}
}

@article{ZA13a-short,
  title={Good practice in large-scale learning for image classification},
  author={Akata, Zeynep and Perronnin, Florent and Harchaoui, Zaid and Schmid, Cordelia},
  journal={IEEE TPAMI},
  year={2013}
}

@INPROCEEDINGS{EA19a,
  author={Akbas, Esra and Aktas, Mehmet Emin},
  booktitle={2019 IEEE International Conference on Big Data}, 
  title={Network Embedding: on Compression and Learning}, 
  year={2019},
  pages={4763--4772}
}

@article{JA11a,
  title   = {{KEEL} Data-Mining Software Tool: Data Set Repository, Integration
                  of Algorithms and Experimental Analysis Framework},
  author  = {Jes{\'{u}}s Alcal{\'{a}}{-}Fdez and
                  Alberto Fern{\'{a}}ndez and
                  Juli{\'{a}}n Luengo and
                  Joaqu{\'{\i}}n Derrac and
                  Salvador Garc{\'{\i}}a},
  journal = {Journal of Multiple-Valued Logic and Soft Computing},
  volume  = {17},
  number  = {2-3},
  pages   = {255--287},
  year    = {2011},
}

@inproceedings{FA96a,
  booktitle = {Proceedings of the Fifth Turkish Artificial Intelligence and Artificial Neural Networks Symposium},
  author = {Alimoglu, Fevzi and Alpaydin, Ethem},
  title = {Methods of combining multiple classifiers based on different representations for pen-based handwritten digit recognition},
  year = {1996}
}


@Article{FA95a,
  author = 	 {F. Alizadeh},
  title = 	 {Interior point methods in semidefinite 
programming with application to combinatorial optimization},
  journal = 	 {SIAM J. Optim.},
  year = 	 {1995},
  volume =	 {5},
  pages =	 {13--51}
}

@TechReport{FA96,
  author = 	 {Farid Alizadeh and Jean-Pierre A. Haeberly and Michael L. Overton},
  title = 	 {Primal-Dual Interior-Point Methods for Semidefinite
                  Programming: convergence Rates, Stability and Numerical Results},
  institution =  {Department of Computer Science, New York University},
  year = 	 {1996},
  number =	 {721},
  month =	 {May},
  note =         {To appear in {\em SIAM J. Optim.}, 1998.} 
}


@Manual{FA97a,
  title = 	 {SDPpack User's Guide, Version 0.9 BETA for {MATLAB} 5.0},
  author =	 {Farid Alizadeh and Jean-Pierre A. Haeberly and 
                  Madhu V. Nayakkankuppam and Michael L. Overton and 
                  Stefan Schmieta},
  organization = {New York University Computer Science Department},
  year =	 {1997},
  note =	 {available at http://www.cs.nyu.edu/faculty/overton/sdppack/sdppack.html}
}
		  
		  
@Article{FA98a,
  author = 	 {Farid Alizadeh and Jean-Pierre A. Haeberly and Michael L. Overton},
  title = 	 {Primal-Dual Interior-Point Methods for Semidefinite
                  Programming: convergence Rates, Stability and Numerical Results},
  journal =	 "SIAM J. Optim.",
  year =	 "1998",
  volume =	 "8",
  number =	 "3",
  pages =	 "746--768"
}



@Article{GA97a,
  author = 	 {G. All\'eon and M. Benzi and L. Giraud},
  title = 	 {Sparse approximate inverse preconditioning for
dense linear systems arising in computational electromagnetics},
  journal = 	 {Numer. Algorithms},
  year = 	 {1997},
  volume =	 {16},
  pages =	 {1--15}
}

@article{ELA01a,
 author = {Erin L. Allwein and Robert E. Schapire and Yoram Singer},
 title = {Reducing multiclass to binary: a unifying approach for margin classifiers},
 journal = {Journal of Machine Learning Research},
 volume = {1},
 year = {2001},
 issn = {1533-7928},
 pages = {113--141},
 publisher = {MIT Press},
 }

@article{ELA01a-short,
 author = {Erin L. Allwein and Robert E. Schapire and Yoram Singer},
 title = {Reducing multiclass to binary: a unifying approach for margin classifiers},
 journal = {JMLR},
 volume = {1},
 year = {2001},
 pages = {113--141}
 }


@article{AU99a, 
 title={Broad patterns of gene expression revealed by clustering analysis of 
tumor and normal colon tissues probed by oligonucleotide arrays}, 
 author={U. Alon and N. Barkai and D. A. Notterman and K. Gish and S. Ybarra and D.Mack and 
A. J. Levine}, 
 journal={Cell Biology}, 
 volume={96}, 
 number={}, 
 pages={6745--6750}, 
 year={1999} 
} 


@article{RA21a,
title = {Multi-label thresholding for cost-sensitive classification},
journal = {Neurocomputing},
volume = {436},
pages = {232--247},
year = {2021},
author = {Reem Alotaibi and Peter Flach},
}

@article{HBA07a,
  title={A choice of forcing terms in inexact {N}ewton method},
  author={An, Heng-Bin and Mo, Ze-Yao and Liu, Xing-Ping},
  journal={Journal of Computational and Applied Mathematics},
  volume={200},
  number={1},
  pages={47--60},
  year={2007}
}


@article{HBA07a-short,
  title={A choice of forcing terms in inexact {N}ewton method},
  author={An, Heng-Bin and Mo, Ze-Yao and Liu, Xing-Ping},
  journal={J. Comput. Appl. Math.},
  volume={200},
  pages={47--60},
  year={2007}
}

@inproceedings{RA02a,
 author = {Ananthakrishna, Rohit and Chaudhuri, Surajit and Ganti, Venkatesh},
 title = {Eliminating fuzzy duplicates in data warehouses},
 booktitle = {Proceedings of the VLDB Endowment},
 year = {2002},
 pages = {586--597},
} 

@book{EA99a,
    author = "Anderson, E. and Bai, Z. and Bischof, C. and Demmel, J. and Dongarra, J. and Du Croz, J. and Greenbaum, A. and Hammarling, S. and McKenney, A. and Ostrouchov, S. and Sorensen, D.",
    title = "{LAPACK} Users' Guide, Release 3.0",
    publisher = "{SIAM}",
    address = "Philadelphia",
    year = "1999"
}

@Book{EJA87,
  author = 	 {E. J. Anderson and P. Nash},
  title = 	 {Linear programming in infinite--dimensional spaces},
  publisher = 	 {Wiley},
  year = 	 {1987},
  address =	 {Chichester}
}

@inproceedings{AA93a,
 author={Andersson, Arne},
 title={Balanced Search Trees made Simple},
 booktitle= {Proceedings of the Third Workshop on Algorithms and Data Structures},
 pages={60--71},
 year={1993}
}

@article{ADA20a,
    title={Graph Representation Learning Network via Adaptive Sampling},
    author={de Andrade, Anderson and Chen Liu},
    year={2020},
    journal = {arXiv preprint arXiv:2006.04637}
}

@InProceedings{GA97b,
  author = 	 {G. Andreu and  A. Crespo and J. M. Valiente},
  title = 	 {Selecting the toroidal self-organizing feature maps ({TSOFM}) best organized to object recognition},
  booktitle = 	 {Proc. ICNN97},
  OPTcrossref =  {},
  OPTkey = 	 {},
  pages =	 {1341--1346},
  year =	 {1997},
  OPTeditor = 	 {},
  volume =	 {2},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTaddress = 	 {},
  OPTmonth = 	 {},
  OPTorganization = {},
  publisher =	 {IEEE},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@inproceedings{GA07a,
   author    = {Galen Andrew and Jianfeng Gao},
   title     = {Scalable Training of {L}1-Regularized Log-Linear Models},
   booktitle = {Proceedings of the Twenty Fourth International Conference 
on Machine Learning (ICML)},
   year      = {2007},
   pages     = {},
}

@inproceedings{GA07a-short,
   author    = {Galen Andrew and Jianfeng Gao},
   title     = {Scalable Training of {L}1-Regularized Log-Linear Models},
   booktitle = {ICML},
   year      = {2007},
   pages     = {},
}

@inproceedings{MLA02a,
author={Maria-Luiza Antonie and Osrnar R. Za\"iane},
booktitle={ICDM},
title={Text document categorization by term association},
year={2002},
pages={19--26}
}


@Book{TMA74a,
  author =       {Tom M. Apostol},
  title =        {Mathematical Analysis},
  publisher =    {Addison-Wesley},
  year =         {1974},
  edition  = {second}
}

@article{MA19a, 
title={Robust Negative Sampling for Network Embedding}, 
journal={Proceedings of the Thirty-third AAAI Conference on Artificial Intelligence (AAAI)}, 
author={Armandpour, Mohammadreza and Ding, Patrick and Huang, Jianhua and Hu, Xia}, 
year={2019}, 
pages={3191--3198}
}

@inproceedings{DA07a,
  title={k-means++ the advantages of careful seeding},
  author={Arthur, David and Vassilvitskii, Sergei},
  booktitle={Proceedings of the Eighteenth Annual ACM-SIAM Symposium on Discrete Algorithms},
  pages={1027--1035},
  year={2007}
}

@Misc{LPA22a,
  author =   {{LibMultiLabel Project Authors}},
  title =    {{LibMultiLabel} User Guide},
  url =  {https://www.csie.ntu.edu.tw/~cjlin/papers/libmultilabel/userguide.pdf},
  year =   {2022}
}

@techreport{BMA92,
author      = {B. M. Averick and R. G. Carter and J. J. Mor\'e and G-L. Xue},
title       = {The {MINPACK-2} test problem collection},
institution = {Mathematics and Computer Science Division,
               Argonne National Laboratory},
year        = {1992},
type        = {Preprint},
number      = {MCS-P153-0694},
}

@Book{MA76a,
  author =	 {Moedecai Avriel},
  title = 	 {Nonlinear Programming},
  publisher = 	 {Prentice-Hall Inc.},
  year = 	 {1976},
  address =	 {New Jersey}
}

@book {OA94,
author      = {O. Axelsson},
title       = {Iterative Solution Methods},
publisher   = {Cambridge University Press},
year        = {1994},
}


@article{MA55a,
  author = {Miriam Ayer and H. D. Brunk and G. M. Ewing and W. T. Reid and Edward Silverman},
  journal = {The Annals of Mathematical Statistics},
  number = {4},
  pages = {641--647},
  publisher = {Institute of Mathematical Statistics},
  title = {An Empirical Distribution Function for Sampling with Incomplete Information},
  volume = {26},
  year = {1955},
}

@inproceedings{RB17a,
author = {Babbar, Rohit and Sch\"{o}lkopf, Bernhard},
title = {Di{SMEC}: Distributed Sparse Machines for Extreme Multi-Label Classification},
year = {2017},
booktitle = {Proceedings of the Tenth ACM International Conference on Web Search and Data Mining (WSDM)},
pages = {721--729}
}

@article{RB19a,
  author = {Babbar, Rohit and Sch\"{o}lkopf, Bernhard},
  title = {Data scarcity, robustness and extreme multi-label classification},
  year = {2019},
  volume = {108},
  journal = {Machine Learning},
  pages = {1329--1351}
}

@inproceedings{FRB05a,
 author = {Bach, Francis R. and Jordan, Michael I.},
 title = {Predictive Low-rank Decomposition for Kernel Methods},
 booktitle = {Proceedings of the Twenty Second International Conference on Machine Learning},
 pages = {33--40},
 year = {2005}
}

@inproceedings{YB14a,
 author = {Bachrach, Yoram and Finkelstein, Yehuda and
Gilad-Bachrach, Ran and Katzir, Liran and Koenigstein, Noam and
Nice, Nir and Paquet, Ulrich},
 title = {Speeding Up the {X}box Recommender System Using a
{E}uclidean Transformation for Inner-product Spaces},
 booktitle = {Proceedings of the 8th ACM Conference on
Recommender Systems},
 year = {2014},
 pages = {257--264}
}

@inproceedings{YB14a-short,
 author = {Bachrach, Yoram and Finkelstein, Yehuda and
Gilad-Bachrach, Ran and Katzir, Liran and Koenigstein, Noam and
Nice, Nir and Paquet, Ulrich},
 title = {Speeding Up the {X}box Recommender System Using a
{E}uclidean Transformation for Inner-product Spaces},
 booktitle = {RecSys},
 year = {2014},
 pages = {257--264}
}

@inproceedings{TZB21a,
author = {Baharav, Tavor Z. and Jiang, Daniel L. and Kolluri, Kedarnath and Sanghavi, Sujay and Dhillon, Inderjit S.},
title = {Enabling Efficiency-Precision Trade-offs for Label Trees in Extreme Classification},
year = {2021},
doi = {10.1145/3459637.3481914},
booktitle = {Proceedings of the 30th ACM International Conference on Information and Knowledge Management (CIKM)},
pages = {3717--3726},
}

@inproceedings{DB15a,
author = "Bahdanau, Dzmitry and Cho, Kyunghyun and Bengio, Yoshua",
editor = "Bengio, Yoshua and LeCun, Yann",
title = "Neural Machine Translation by Jointly Learning to Align and Translate",
booktitle = "Proceedings of the Third International Conference on Learning Representations (ICLR)",
year = "2015",
}

@InProceedings{CB02a,
  author = {Claus Bahlmann and Bernard Haasdonk and Hans Burkhardt},
  title = {On-line Handwritting Recognition with Support Vector Machines
           -- A Kernel Approach},
   year = {2002},
  booktitle = {Proc. of the 8th Int.Workshop on Frontiers in Handwriting
               Recognition(IWFHR)},
  pages = {49--54}
}

@article{SB15c,
  title={Automatic semantic classification of scientific literature according to the hallmarks of cancer},
  author={Baker, Simon and Silins, Ilona and Guo, Yufan and Ali, Imran and H{\"o}gberg, Johan and Stenius, Ulla and Korhonen, Anna},
  journal={Bioinformatics},
  volume={32},
  number={3},
  pages={432--440},
  year={2015}
}

@incollection{GHB05a,
 author = {G\"{o}khan H. {Bak{\i}r} and L\'{e}on {Bottou} and Jason {Weston}},
 title = {Breaking SVM Complexity with Cross-Training},
 booktitle = {Advances in Neural Information Processing Systems 17},
 editor = {Lawrence K. Saul and Yair Weiss and {L\'{e}on} Bottou},
 publisher = {MIT Press},
 address = {Cambridge, MA},
 pages = {81--88},
 year = {2005},
 original = "0081_384.PDF",
}

@article{RB89a,
title={Accelerated backpropagation learning: Two optimization methods},
author={Battiti, Roberto},
journal={Complex systems},
volume={3},
number={4},
pages={331--342},
year={1989}
}

@inproceedings{IB04a,
    author = {Bhattacharya, Indrajit and Getoor, Lise},
    booktitle = {Proceedings of the 9th ACM SIGMOD Workshop on Research Issues in Data Mining and Knowledge Discovery},
    pages = {11--18},
    title = {Iterative record linkage for cleaning and integration},
    year = {2004}
}

@inproceedings{PB11a,
  author={Balamurugan, P. and Shevade, Shirish Krishnaj and Sundararajan, Sellamanickam and Keerthi, S. Sathiya},
  title={A sequential dual method for structural {SVM}s},
 booktitle = {Proceedings of the 2011 SIAM International Conference on Data Mining},
 pages = {223--234},
 year={2011},
}

@inproceedings{FB18a,
author = "Barbieri, Francesco and Espinosa-Anke, Luis and Camacho-Collados, Jose and Schockaert, Steven and Saggion, Horacio",
title = "Interpretable Emoji Prediction via Label-Wise Attention {LSTM}s",
booktitle = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
year = "2018",
doi = "10.18653/v1/D18-1508",
pages = "4766--4771",
}

@inproceedings{FB20a,
  title = "{T}weet{E}val: Unified Benchmark and Comparative Evaluation for Tweet Classification",
  author = "Barbieri, Francesco  and
  Camacho-Collados, Jose  and
  Espinosa Anke, Luis  and
  Neves, Leonardo",
  editor = "Cohn, Trevor  and
  He, Yulan  and
  Liu, Yang",
  booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
  year = "2020",
  doi = "10.18653/v1/2020.findings-emnlp.148",
  pages = "1644--1650",
}

@Book{VB86a,
  author =	 {V. Barbu and Th. Precupanu},
  title = 	 {Convexity and Optimization in {B}anach Spaces},
  publisher = 	 {D. Reidel},
  year = 	 {1986},
  address =	 {Dordrecht}
}

@InProceedings{RRB93a,
  author = 	 {R. R. Bailey and E. J. Pettit and R. T. Borochoff and M.
		  T. Manry and X. Jiang},
  title = 	 {Automatic Recognition of USGS Land Use/Cover Categories
		  Using Statistical and Neural Networks Classifiers},
  booktitle = 	 {SPIE OE/Aerospace and Remote Sensing},
  address = {Bellingham, WA},
  publisher = {SPIE},
  year =	 {1993}
}



@Article{SB05a,
  author = 	 {Suhrid Balakrishnan and David Madigan},
  title = 	 {Algorithms for sparse linear classifiers in the massive data setting},
  journal={Journal of Machine Learning Research},  
 issue_date = {6/1/2008},
 volume = {9},
 year = {2008},
 pages = {313--337}
} 
  
  url={http://www.stat.rutgers.edu/~madigan/PAPERS/sm.pdf},
  OPTkey = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTpages = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@article{PB14a,
  title={Searching for exotic particles in high-energy physics with deep learning},
  author={Pierre Baldi and Peter Sadowski and Daniel Whiteson},
  journal={Nature Communications},
  volume={5},
  year={2014}
}

@Misc{JB01a,
  author =   {Jason Baldridge and Tom Morton and Gann Bierner},
  title =    {{O}pen{NLP} package },
  year =     {2001},
  url = {http://opennlp.sourceforge.net/}
}


@inproceedings{GB15a,
 title={Diamond sampling for approximate maximum all-pairs
dot-product ({MAD}) search},
 author={Ballard, Grey and Pinar, Ali and Kolda, Tamara G and
Seshadri, C},
 booktitle = {Proceedings of the IEEE International Conference
on Data Mining (ICDM)},
 year={2015}
}

@inproceedings{GB15a-short,
 title={Diamond sampling for approximate maximum all-pairs
dot-product ({MAD}) search},
 author={Ballard, Grey and Pinar, Ali and Kolda, Tamara G and
Seshadri, C},
 booktitle = {ICDM},
 year={2015}
}

@article{TVB07a,
  title={Statistical criteria for early-stopping of support vector machines},
  author={Bandos, Tatyana V. and Camps-Valls, Gustavo and Soria-Olivas, Emilio},
  journal={Neurocomputing},
  volume={70},
  number={13-15},
  pages={2588--2592},
  year={2007}
}

@article{TVB07a-short,
  title={Statistical criteria for early-stopping of support vector machines},
  author={Bandos, Tatyana V. and Camps-Valls, Gustavo and Soria-Olivas, Emilio},
  journal={Neurocomputing},
  year={2007}
}

@inproceedings{AB07a,
  title={Fast Hyperspectral Anomaly Detection via {SVDD}},
  author={Banerjee, Amit and Burlina, Philippe and Meth, Reuven},
  booktitle = {Proceedings of IEEE International Conference on Image Processing},
  year={2007},
  organization={IEEE}
}
%  pages={IV--101},


@Article{JB88a,
  author = {Jonathan Barzilai and Jonathan M. Borwein},
  title = {Two-Point Step Size Gradient Methods},
  journal = {IMA Journal of Numerical Analysis},
  year = {1988},
  pages = {141--148},
  volume = {8}
}
@article{JBHU84a,
	title={Generalized {H}essian matrix and second-order optimality
		conditions for problems with $C^{L1}$ data},
	author={Hiriart-Urruty, Jean-Baptiste and Strodiot,
		Jean-Jacques and Nguyen, V Hien},
	journal={Applied mathematics and optimization},
	volume={11},
	number={1},
	pages={43--56},
	year={1984},
	publisher={Springer}
}

@article{JBHU84a-short,
	title={Generalized {H}essian matrix and second-order optimality
		conditions for problems with $C^{L1}$ data},
	author={Hiriart-Urruty, Jean-Baptiste and Strodiot,
		Jean-Jacques and Nguyen, V Hien},
	journal={Appl. Math. Optim.},
	volume={11},
	number={1},
	pages={43--56},
	year={1984},
	publisher={Springer}
}


@book{JBHU01a,
  title={Fundamentals of convex analysis},
  author={Jean-Baptiste Hiriart-Urruty and Lemar{\'e}chal, Claude},
  year={2001},
  publisher={Springer Verlag}
}

@inproceedings{MB94a,
  title={Interprocessor collective communication library ({I}nter{C}om)},
  author={Barnett, Mike and Gupta, Satya and Payne, David G. and
Shuler, Lance and van De Geijn, Robert and Watts, Jerrell},
  booktitle={Proceedings of the Scalable High-Performance Computing Conference},
  pages={357--364},
  year={1994}
}

@article{MBB00a,
  title={Automatic differentiation of algorithms},
  author={Bartholomew-Biggs, Michael and Brown, Steven and Christianson, Bruce and Dixon, Laurence},
  journal={Journal of Computational and Applied Mathematics},
  volume={124},
  number={1-2},
  pages={171--190},
  year={2000}
}

@INPROCEEDINGS{RAB17a,
  author={Bauder, Richard A. and Khoshgoftaar, Taghi M.},
  booktitle={Proceedings of IEEE International Conference on Information Reuse and Integration}, 
  title={Estimating Outlier Score Probabilities}, 
  year={2017},
  pages={559--568}
}

@article{AGB18a,
  title={Automatic differentiation in machine learning: a survey},
  author={Baydin, Atilim Gunes and Pearlmutter, Barak A. and Radul, Alexey Andreyevich and Siskind, Jeffrey Mark},
  journal={Journal of Machine Learning Research},
  volume  = {18},
  number  = {153},
  pages   = {1-43},  
  year={2018}
}

@article{AGB18a-short,
  title={Automatic differentiation in machine learning: a survey},
  author={Baydin, Atilim Gunes and Pearlmutter, Barak A. and Radul, Alexey Andreyevich and Siskind, Jeffrey Mark},
  journal={JMLR},
  volume  = {18},
  pages   = {1-43},  
  year={2018}
}

@inproceedings{IB17a,
title={A generic coordinate descent framework for learning from implicit feedback},
author={Bayer, Immanuel and He, Xiangnan and Kanagal, Bhargav and Rendle, Steffen},
booktitle={Proceedings of the 26th International Conference on World Wide Web},
pages={1341--1350},
year={2017}
}

@inproceedings{IB17a-short,
title={A generic coordinate descent framework for learning from implicit feedback},
author={Bayer, Immanuel and He, Xiangnan and Kanagal, Bhargav and Rendle, Steffen},
booktitle={WWW},
year={2017}
}


@article{RB72a,
author= {Bayer, Rudolf},
title= {Symmetric binary {B}-Trees: Data structure and maintenance algorithms},
journal= {Acta Informatica},
year= {1972},
volume= {1},
issue= {4},
pages= {290--306}
}


@Book{MSB93a,
  author =	 {Mokhtar S. Bazaraa and Hanif D. Sherali and C. M. Shetty},
  title = 	 {Nonlinear programming : theory and algorithms},
  publisher = 	 {Wiley},
  year = 	 {1993},
  edition =	 {Second}
}

@article{AB09b,
  title = {A Fast Iterative Shrinkage-thresholding Algorithm for Linear Inverse Problems},
  author = {Beck, Amir and Teboulle, Marc},
  journal = {SIAM Journal on Imaging Sciences},
  volume = {2},
  number = {1},
  pages = {183--202},
  year = {2009}
}

@article{AB13a,
title={On the convergence of block coordinate descent type methods},
author={Beck, Amir and Tetruashvili, Luba},
journal={SIAM Journal on Optimization},
volume={23},
number={4},
pages={2037--2060},
year={2013},
publisher={SIAM}
}

@Article{AB14a,
author="Beck, Amir",
title="The 2-Coordinate Descent Method for Solving Double-Sided Simplex Constrained Minimization Problems",
journal="Journal of Optimization Theory and Applications",
year="2014",
volume="162",
number="3",
pages="892--919"
}


@Article{AB14a-short,
author="Beck, Amir",
title="The 2-Coordinate Descent Method for Solving Double-Sided Simplex Constrained Minimization Problems",
journal     = {J. Optim. Theory Appl.},
year="2014",
volume="162",
number="3",
pages="892--919"
}

@techreport{RB04a,
  author={Ron Bekkerman and James Allan},
  title={Using Bigrams in Text Categorization},  
  number={IR-408},
  year={2004},
  institution={UMass Amherst}
}

@inproceedings{RB04b,
  title={Query recommendation using query logs in search engines},
  author={Baeza-Yates, Ricardo and Hurtado, Carlos and Mendoza, Marcelo},
  booktitle={International Conference on Extending Database Technology},
  pages={588--596},
  year={2004}
}

@inproceedings{RB04b-short,
  title={Query recommendation using query logs in search engines},
  author={Baeza-Yates, Ricardo and Hurtado, Carlos and Mendoza, Marcelo},
  booktitle={EDBT},
  year={2004}
}

@inproceedings{RB08a,
author ={Ron Bekkerman and Martin Scholz},
	title ={Data Weaving: Scaling Up the State-Of-The-Art in Data Clustering},
	booktitle ={Proceedings of CIKM},
	year ={2008},
	pages ={1083--1092}
}

@INPROCEEDINGS{RB11a,
        author = {Ron Bekkerman and Matan Gavish},
        title = {High-precision phrase-based document classification on a modern scale},
        booktitle = {Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining},                                               
        year = {2011},
        pages = {231--239},
        publisher = {ACM},
        address = {New York, NY, USA}
} 


@INPROCEEDINGS{RB11a-short,
  AUTHOR ={Ron Bekkerman and Matan Gavish},
  TITLE ={High-Precision Phrase-Based Document Classification on a Modern Scale},
  BOOKTITLE ={KDD},
  YEAR ={2011}
}

@inproceedings{RB07a,
        author = {R. Bell and Y. Koren and C. Volinsky},
        title = {Modeling relationships at multiple scales to improve accuracy of large recommender systems},
        booktitle = {KDD '07: Proceedings of the 13th ACM SIGKDD international conference on Knowledge discovery and data mining},
        year = {2007},
        isbn = {978-1-59593-609-7},
        pages = {95--104},
        location = {San Jose, California, USA},
        doi = {http://doi.acm.org/10.1145/1281192.1281206},
        publisher = {ACM},
        address = {New York, NY, USA},
}

@article{RB07b,
        author = {R. Bell and Y. Koren and C. Volinsky},
        title = {The {B}ell{K}or solution to the {N}etflix {P}rize},
        year = {2007},
	url = {http://www.research.att.com/~volinsky/netflix/ProgressPrize2007BellKorSolution.pdf}	
}

@article{RB07c,
 author = {Bell, Robert M. and Koren, Yehuda},
 title = {Lessons from the {N}etflix prize challenge},
 journal = {ACM SIGKDD Explorations Newsletter},
 issue_date = {December 2007},
 volume = {9},
 number = {2},
 year = {2007},
 pages = {75--79}
}

@article{RB07c-short,
 author = {Bell, Robert M. and Koren, Yehuda},
 title = {Lessons from the {N}etflix prize challenge},
 journal = {SIGKDD Explor. Newsl.},
 year = {2007},
 pages = {75--79},
}

@Book{RB95a,
  author = 	 {R. Bellman},
  title = 	 {Introduction to Matrix Analysis},
  publisher = 	 {Society for Industrial and Applied Mathematics},
  year = 	 {1995},
  address =	 {Philadelphia}
}




@article{IB20a,
  author       = {Iz Beltagy and
                  Matthew E. Peters and
                  Arman Cohan},
  title        = {Longformer: The Long-Document Transformer},
  journal      = {CoRR},
  volume       = {abs/2004.05150},
  year         = {2020},
  url          = {https://arxiv.org/abs/2004.05150},
  eprinttype    = {arXiv}
}

@article{YB94a,
  title={Learning long-term dependencies with gradient descent is difficult},
  author={Bengio, Yoshua and Simard, Patrice and Frasconi, Paolo},
  journal={IEEE Transactions on Neural Networks},
  volume={5},
  number={2},
  pages={157--166},
  year={1994}
}


@inproceedings{YB03a,
  title={Quick Training of Probabilistic Neural Nets by Importance Sampling},
  author={Bengio, Yoshua and Sen{\'e}cal, Jean-S{\'e}bastien},
  booktitle = {Proceedings of the Ninth International Workshop on Artificial Intelligence and Statistics},
  pages = {17--24},
  year = {2003},
} 

@incollection{YB07a,
  title={Scaling learning algorithms towards {AI}},
  author={Bengio, Yoshua and {LeCun}, Yann},
  pages = {321--360},
  editor = {Bottou, L\'{e}on and Chapelle, Olivier and {DeCoste},
Dennis and Weston, Jason},
  booktitle = {Large Scale Kernel Machines},
  publisher = {MIT Press},
  address = {Cambridge, MA.},
  year = {2007}
}

@inproceedings{JRB17a,
 author = {Benetka, Jan R. and Balog, Krisztian and N{\o}rv{\aa}g, Kjetil},
 title = {Anticipating Information Needs Based on Check-in Activity},
 booktitle = {Proceedings of the Tenth ACM International Conference on Web Search and Data Mining (WSDM)},
 year = {2017},
 pages = {41--50}
}

@inproceedings{JRB17a-short,
 author = {Benetka, Jan R. and Balog, Krisztian and N{\o}rv{\aa}g, Kjetil},
 title = {Anticipating Information Needs Based on Check-in Activity},
 booktitle = {WSDM},
 year = {2017}
}

@article{JB07a,
        author    = {J. Bennett and S. Lanning},
        title     = {The {N}etflix {P}rize},
        journal   = {Proceedings of KDD Cup and Workshop},
        year      = {2007},
}
		  
@Article{KPB92a,
  author = 	 {K. P. Bennett and O. L. Mangasarian},
  title = 	 {Robust linear programming discrimination of two linear inseparable sets},
  journal = 	 {Optimization Methods and Software},
  year = 	 {1992},
  volume =	 {1},
  pages =	 {23--34}
}

@TechReport{KPB98a,
  author	= {K. P. Bennett and D. Hui and L. Auslender},
  title		= {On Support Vector Decision Trees for Database Marketing},
  month		= mar,
  year		= {1998},
  institution	= {Rensselaer Polytechnic Institute},
  number	= {Math Report No. 98-100},
  type		= {Department of Mathematical Sciences},
  address	= {Troy, NY 12180},
  url		= {http://www.math.rpi.edu/~bennek/}
}

@article{KPB00a,
    author = "Kristin P. Bennett and Nello Cristianini and John Shawe-Taylor and Donghui Wu",
    title = "Enlarging the Margins in Perceptron Decision Trees",
    journal = "Machine Learning",
    volume = "41",
    number = "3",
    pages = "295--313",
    year = "2000",
    url = "citeseer.ist.psu.edu/bennett99enlarging.html" 
}


@TechReport{SB01a,
address     = {Argonne, Illinois},
author      = {Benson, Steven and Jorge J. Mor\'e},
institution = {Mathematics and Computer Science Division, 
               Argonne National Laboratory},
title={A limited memory variable metric method for bound constrained minimization},
year        = {2001},
type        = {Preprint},
number      = {MCS-P909-0901}
}

@TechReport{SB01a-short,
author      = {Benson, Steven and Jorge J. Mor\'e},
title={A limited memory variable metric method for bound constrained minimization},
institution = {Argonne Lab.},
year        = {2001}
}

@book{JB16a,
  title={Programming pearls},
  author={Bentley, Jon},
  edition = {Second},  
  year={2016},
  publisher={Addison-Wesley Professional}
}

@Article{MB98a,
  author = 	 "M. Benzi and R. Kouhia and M. Tuma",
  title = 	 "An assessment of some preconditioning techniques
   in shell problems",
  journal =	 "Comm. Numer. Methods Engrg.",
  year =	 "1998",
  volume =	 "14",
  pages =	 "897--906"
}

@article{MB96,
author      = {Michele Benzi and Carl D. Meyer and Miroslav Tuma},
title       = {A sparse approximate inverse preconditioner for the
               conjugate gradient method},
journal     = {SIAM J. Sci. Comput.},
pages       = {1135--1149},
volume      = {17},
year        = {1996}
}




@TechReport{MB97a,
  author = 	 {M. Benzi and R. Kouhia and M. Tuma},
  title = 	 {An Assessment of Some Preconditioning Techniques in Shell
   Problems },
  institution =  {LLNL},
  year = 	 {1997},
  number =	 {LA-UR-97-3892},
  annote =	 {To appear (in revised form) in Communications in
   Numerical Methods in Engineering}
}

@article{ASB17a,
  title={An Investigation of {N}ewton-Sketch and Subsampled {N}ewton Methods},
  author={Albert S. Berahas and Raghu Bollapragada and Jorge Nocedal},
  note={arXiv preprint arXiv:1705.06211},
  year={2017}
}

@article{ASB17a-short,
  title={An Investigation of {N}ewton-Sketch and Subsampled {N}ewton Methods},
  author={Albert S. Berahas and Raghu Bollapragada and Jorge Nocedal},
  note={arXiv},
  year={2017}
}

@INPROCEEDINGS{DB18a,
  author={Berberidis, Dimitris and Nikolakopoulos, Athanasios N. and Giannakis, Georgios B.},
  booktitle={Proceedings of IEEE International Conference on Big Data}, 
  title={Ada{DIF}: Adaptive Diffusions for Efficient Semi-supervised Learning over Graphs}, 
  year={2018},
  pages={92--99}
}

@inproceedings{DB19a,
title={Node Embedding via Adaptive Similarities},
author={Dimitris Berberidis and Georgios B. Giannakis},
booktitle={Proceedings of the 15th International Workshop on Mining and Learning with Graphs},
year={2019}
}

@ARTICLE{DB19b,
  author={Berberidis, Dimitris and Nikolakopoulos, Athanasios N. and Giannakis, Georgios B.},
  journal={IEEE Transactions on Signal Processing}, 
  title={Adaptive Diffusions for Scalable Learning Over Graphs}, 
  year={2019},
  volume={67},
  pages={1307--1321}
}

@ARTICLE{DB21a,
  author={Berberidis, Dimitris and Giannakis, Georgios B.},
  journal={IEEE Transactions on Knowledge and Data Engineering},
  title={Node Embedding with Adaptive Similarities for Scalable Learning over Graphs},
  year={2021},
  volume={33},
  pages={637--650},
}

@Book{CB84a,
  author =       {C. Berg and  J. P .R. Christensen and P. Ressel},
  title =        {Harmonic Analysis on              
 Semigroups},
  publisher =    {Springer-Verlag},
  year =         {1984},
  address =      {New York}
}

@ARTICLE{MB04b,
 author={Bilenko, Mikhail and Mooney, Raymond and Cohen, William and Ravikumar, Pradeep and Fienberg, Stephen},
 journal={IEEE Intelligent Systems},
 title={Adaptive name matching in information integration},
 year={2003},
 volume={18},
 number={5},
 pages={16-23},
}

@Article{AB96,
   author = 	 {Berger, Adam L. and Della Pietra, Vincent J. and Della Pietra, Stephen A.},
   title = 	 {A Maximum Entropy Approach to Natural Language Processing},
   journal = 	 {Computational Linguistics},
   year = 	 {1996},
   OPTkey = 	 {},
   volume =	 {22},
   number =	 {1},
   pages =	 {39--71},
   OPTmonth = 	 {},
   OPTnote = 	 {},
   OPTannote = 	 {}
}




@Misc{AB97a,
  author = {Adam Berger},
  title = {Improved Iterative Scaling Algorithm: A Gentle Introduction},
  institution =  {School of Computer Science, Carnegie Mellon University},
  year =         {1997},
  month =        {December}
}

@TechReport{RB02a,
  author = 	 {Ruth Bergman and Martin Griss and Carl Staelin},
  title = 	 {A Personal Email Assistant},
  institution =  {HP Laboratories},
  year = 	 {2002},
  number =	 {HPL-2002-236},
  address =	 {Palo Alto, CA}
}


@Article{MB06a,
  author = 	 {Michael Berry and Murray Browne and  Amy Langville and  Paul Pauca and Robert Plemmon},
  title = 	 {Algorithms and Applications for Approximate Nonnegative Matrix Factorization},
  journal = 	 {Computational Statistics and Data Analysis},
  year = 	 {2007},
  OPTkey = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTpages = 	 {},
  OPTmonth = 	 {},
  note =	 {Submitted},
  OPTannote = 	 {}
}

@Inproceedings{TBM11a,
author          = {Thierry Bertin-Mahieux and Daniel P.W. Ellis
and Brian Whitman and Paul Lamere},
title           = {The Million Song Dataset},
booktitle       = {In Proceedings of the Twelfth International
Society for Music Information Retrieval Conference (ISMIR
2011)},
year            = {2011}
}

@Article{DPB76a,
  author = 	 {Dimitri P. Bertsekas},
  title = 	 {On the {G}oldstein-{L}evitin-{P}olyak gradient projection method},
  journal = 	 {IEEE Transactions on Automatic Control},
  year = 	 {1976},
  volume =	 {21},
  pages =	 {174--184}
}

@book {DPB82a,
author      = {Dimitri P. Bertsekas},
title       = {Constrained Optimization and Lagrange Multiplier Methods},
publisher   = {Academic Press},
year        = {1982}
}

@book{DPB89a,
  title={Parallel and Distributed Computation: Numerical Methods},
  author={Bertsekas, Dimitri P. and Tsitsiklis, John N.},
  volume={23},
  year={1989},
  publisher={Prentice Hall Englewood Cliffs, NJ}
}

@article{DPB94a,
author = {Bertsekas, Dimitri P. and Tseng, Paul},
title = {Partial Proximal Minimization Algorithms for Convex Pprogramming},
journal = {SIAM Journal on Optimization},
volume = {4},
number = {3},
pages = {551--572},
year = {1994}
}

@Book{DPB95a,
 author      = {Dimitri P. Bertsekas},
  title = 	 {Nonlinear Programming},
  publisher = 	 {Athena Scientific},
  year = 	 {1999},
  edition =	 {Second},
  address =	 {Belmont, MA 02178-9998}
}

@article{SB22a,
  title={We need to talk about random seeds}, 
  author={Steven Bethard},
  year={2022},
  eprint={2210.13393},
  archivePrefix={arXiv},
  primaryClass={cs.CL}
}

@inproceedings{AB09d,
author = {Beygelzimer, Alina and Langford, John and Lifshits, Yuri and Sorkin, Gregory and Strehl, Alex},
title = {Conditional probability tree estimation analysis and algorithms},
year = {2009},
booktitle = {Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence},
pages = {51--58}
}

@inproceedings{KB15a,
  title = {Sparse Local Embeddings for Extreme Multi-label Classification},
  author = {Bhatia, Kush and Jain, Himanshu and Kar, Purushottam and Varma, Manik and Jain, Prateek},
  booktitle = {Advances in Neural Information Processing Systems 28},
  editor = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  pages = {730--738},
  year = {2015}
} 

@inproceedings{KB15a-short,
  title = {Sparse Local Embeddings for Extreme Multi-label Classification},
  author = {Bhatia, Kush and Jain, Himanshu and Kar, Purushottam and Varma, Manik and Jain, Prateek},
  booktitle = {NIPS},
  year = {2015}
} 

@Misc{KB16a,
  author    = {Kush Bhatia and Kunal Dahiya and Himanshu Jain and Purushottam Kar and Anshul Mittal and Yashoteja Prabhu and Manik Varma},
  title     = {The extreme classification repository: Multi-label datasets and code},
  url       = {http://manikvarma.org/downloads/XC/XMLRepository.html},
  year      = {2016}
}

@inproceedings{YB13a,
author= {Yatao Bian and Xiong Li and Mingqi Cao and Yuncai
Liu},
title = {Bundle {CDN}: a highly parallelized approach for
large-scale l1-regularized logistic regression},
booktitle = "Proceedings of European Conference on Machine Learning and
Principles and Practice of Knowledge Discovery in Databases (ECML/
PKDD)",
year= "2013"
}

@inproceedings{YB13a-short,
author= {Yatao Bian and Xiong Li and Mingqi Cao and Yuncai
Liu},
title = {Bundle {CDN}: a highly parallelized approach for
large-scale l1-regularized logistic regression},
booktitle = "ECML/PKDD",
year= "2013"
}

@book{SB09a,
  author = {Bird, Steven and Klein, Ewan and Loper, Edward},
  publisher = {O'Reilly},
  title = {Natural Language Processing with {P}ython: Analyzing Text with the Natural Language Toolkit},
  year = {2009}
}

@Article{EGB00a,
  author = {Ernesto G. Birgin and Jos\'e M. Mart\'inez and Marcos Raydan},
  title = {Nonmonotone Spectral Projected Gradient Methods on Convex Sets},
  journal = {SIAM Journal on Optimization},
  year = {2000},
  pages = {1196--1211},
  volume = {10}
}

@Book{CMB95a,
  author =	 {Bishop, C. M.},
  title = 	 {Neural Networks for
Pattern Recognition},
  publisher = 	 {Oxford University
Press},
  year = 	 {1995},
  address =	 {Oxford}
}

@book{CMB06a,
 author = {Bishop, Christopher M.},
 title = {Pattern Recognition and Machine Learning},
 year = {2006},
 isbn = {0387310738},
 publisher = {Springer-Verlag New York, Inc.},
} 

@book{CMB06a-short,
 author = {Bishop, Christopher M.},
 title = {Pattern Recognition and Machine Learning},
 year = {2006},
 publisher = {Springer-Verlag},
} 

@article{MJA99,
author = {Blackard, J. A. and Dean, D. J.},
title = {Comparative accuracies of artificial neural networks and
         discriminant analysis in predicting forest cover types
         from cartographic variables},
journal ={Computers and Electronics in Agriculture},
year    ={1999},
volume  ={24},
pages   ={131--151}
}

@misc{CLB98a,
    author = "Arthur Asuncion and David J. Newman",
    year = "2007",
    title = "{UCI} Machine Learning Repository",
    url = "http://www.ics.uci.edu/~mlearn/MLRepository.html",
    institution = "University of California, Irvine, School of Information and Computer Sciences" }


@misc{CLB98a-short,
    author = "A. Asuncion and D.J. Newman",
    year = "2007",
    title = "{UCI} Machine Learning Repository",
    url = "http://www.ics.uci.edu/$\sim$mlearn/{MLR}epository.html",
    institution = "University of California, Irvine, School of Information and Computer Sciences" }

@inproceedings{GB18a,
title={Adaptive sampled softmax with kernel based sampling},
author={Blanc, Guy and Rendle, Steffen},
booktitle={International Conference on Machine Learning},
pages={590--599},
year={2018}
}

@article{DMB03a,
  title={Latent {D}irichlet allocation},
  author={Blei, David M. and Ng, Andrew Y. and Jordan, Michael I.},
  journal={Journal of Machine Learning Research},
  volume={3},
  pages={993--1022},
  year={2003}
}

@article{DMB12a,
  title={Probabilistic topic models},
  author={Blei, David M.},
  journal={Communications of the ACM},
  volume={55},
  number={4},
  pages={77--84},
  year={2012}
}


@misc{LB18a,
  title={Learning with Random Learning Rates},
  author={Blier, L{\'e}onard and Wolinski, Pierre and Ollivier, Yann},
  note={arXiv preprint arXiv:1810.01322},
  year={2018}
}

@inproceedings{MB16a,
    author = {Mathieu Blondel and Masakazu Ishihata and Akinori Fujino and Naonori Ueda},
    title = {Polynomial Networks and Factorization Machines: new Insights and Efficient Training Algorithms},
    booktitle = {Proceedings of the 33rd International Conference on Machine Learning (ICML)},
    year = {2016}
}

@inproceedings{MB16a-short,
    author = {Mathieu Blondel and Masakazu Ishihata and Akinori Fujino and Naonori Ueda},
    title = {Polynomial Networks and Factorization Machines: new Insights and Efficient Training Algorithms},
    booktitle = {ICML},
    year = {2016}
}

@article{DAB16a,
  title={A comparison of efficient approximations for a weighted sum of chi-squared random variables},
  author={Bodenham, Dean A. and Adams, Niall M.},
  journal={Statistics and Computing},
  volume={26},
  number={4},
  pages={917--928},
  year={2016}
}

@article{RB18a,
    author = {Bollapragada, Raghu and Byrd, Richard H and Nocedal, Jorge},
    title = "{Exact and inexact subsampled {N}ewton methods for optimization}",
    journal = {IMA Journal of Numerical Analysis},
    volume = {39},
    number = {2},
    pages = {545-578},
    year = {2018}
}

@article{RB18a-short,
    author = {Bollapragada, Raghu and Byrd, Richard H and Nocedal, Jorge},
    title = "{Exact and inexact subsampled {N}ewton methods for optimization}",
    journal = {IMA J. Numer. Anal.},
    volume = {39},
    pages = {545-578},
    year = {2018}
}


@article{SB11a,
    title={Inexact block coordinate descent methods with application to
non-negative matrix factorization},
    author={Silvia Bonettini},
    journal={IMA Journal of Numerical Analysis},
    year={2011},
    note={To appear}
}

@article{BCGT95,
author      = {I. Bongartz and A. R. Conn and
               N. I. M. Gould and Ph. L. Toint},
title       = {{\sf CUTE}: {C}onstrained and {U}nconstrained {T}esting
              {E}nvironment},
journal     = {ACM Trans. Math. Software},
volume      = {21},
number      = {1},
pages       = {123--160},
year        = {1995}
}


@Article{JFB98a,
  author = 	 {J. Fr\'ed\'eric Bonnans and Alexander Shapiro},
  title = 	 {Optimization problems with perturbations: a guided tour},
  journal = 	 {SIAM Review},
  year = 	 {1998},
  volume =	 {40},
  number =	 {2},
  pages =	 {228--264}
}


@Book{JFB00a,
  author = 	 {J. Fr\'ed\'eric Bonnans and Alexander Shapiro},
  title = 	 {Pertubation analysis of optimization problems},
  year = 	 {2000},
  publisher = 	 {Springer-Verlag}
}

@inproceedings{SB18a,
author = {Bonner, Stephen and Vasile, Flavian},
title = {Causal Embeddings for Recommendation},
booktitle = {Proceedings of the 12th ACM Conference on Recommender Systems},
year = {2018},
pages = {104--112}
}

@inproceedings{SB18a-short,
author = {Bonner, Stephen and Vasile, Flavian},
title = {Causal Embeddings for Recommendation},
booktitle = {RecSys},
year = {2018}
}

@TechReport{BB97a,
  author = 	 {Brian Borchers},
  title = 	 {{CSDP}, A {C} Library for Semidefinite Programming},
  institution =  {Department of Mathematics, New Mexico Tech.},
  year = 	 {1997},
  address =	 {Socorro, NM 87801},
  month =	 {March},
  note =	 {Available at http://www.nmt.edu/\~{ }borchers/csdp.html},
}

@article{AB05a,
 author = {Antoine Bordes and Seyda Ertekin and Jason Weston and L\'{e}on Bottou},
 title = {Fast Kernel Classifiers with Online and Active Learning},
 journal = {Journal of Machine Learning Research},
 volume = {6},
 pages = {1579--1619},
 year = {2005}
}

@inproceedings{AB07a-short,
   author = {Antoine Bordes and Leon Bottou and Patrick Gallinari and
Jason Weston},
   title = {Solving multiclass support vector machines with {LaRank}},
   booktitle = {ICML},
   year = {2007},
}

@article{AB09a,
  title={{SGD-QN}: Careful quasi-{N}ewton stochastic gradient descent},
   author = {Antoine Bordes and Leon Bottou and Patrick Gallinari},
  journal={Journal of Machine Learning Research},
  volume={10},
  pages={1737--1754},
  year={2009}
}

@article{AB09a-short,
  title={{SGD-QN}: Careful quasi-{N}ewton stochastic gradient descent},
   author = {Antoine Bordes and Leon Bottou and Patrick Gallinari},
  journal={JMLR},
  volume={10},
  pages={1737--1754},
  year={2009}
}

@article{AB10a,
 author = {Bordes, Antoine and Bottou, L\'{e}on and Gallinari, Patrick and Chang, Jonathan and Smith, S. Alex},
 title = {Erratum: {SGD-QN} is Less Careful than Expected},
 journal = {Journal of Machine Learning Research},
 volume = {11},
 pages = {2229--2240},
 year = {2010}
}

@misc{DB08a,
    title={{HDFS} architecture guide},
    author={Borthakur, Dhruba},
    year={2008}
}

@InProceedings{BB92a,
  author = 	 {Bernhard E. Boser and Isabelle Guyon and Vladimir Vapnik},
  title = 	 {A training
     algorithm for optimal margin
     classifiers},
  booktitle = 	 {Proceedings of the Fifth Annual
     Workshop on Computational
     Learning Theory},
  year =	 {1992},
  publisher =	 {ACM Press},
  pages={144--152}
}


@InProceedings{BB92a-short,
  author = 	 {B. E. Boser and I. Guyon and V. Vapnik},
  title = 	 {A training
     algorithm for optimal margin
     classifiers},
  booktitle = 	 {COLT},
  year =	 {1992}
}

@inproceedings{AB17a,
   title={Practical {G}auss-{N}ewton Optimisation for Deep Learning},
   author={Botev, Aleksandar and Ritter, Hippolyt and Barber, David},
  booktitle = 	 {Proceedings of the 34th International Conference on Machine Learning},
   pages={557--565},
   year={2017}
}

@article{LB15a,
  title={A choice of forcing terms in inexact {N}ewton iterations with application to pseudo-transient continuation for incompressible fluid flow computations},
  author={Lorenzo Botti},
  journal={Applied Mathematics and Computation},
  volume={266},
  pages={713--737},
  year={2015}
}

@article{LB15a-short,
  title={A choice of forcing terms in inexact {N}ewton iterations with application to pseudo-transient continuation for incompressible fluid flow computations},
  author={Lorenzo Botti},
  journal={Appl. Math. Comput.},
  volume={266},
  pages={713--737},
  year={2015}
}


@article{LB91a,
  title={Stochastic gradient learning in neural networks},
  author={Bottou, L{\'e}on},
  journal={Proceedings of Neuro-N{\i}mes},
  volume={91},
  number={8},
  year={1991}
}


@InProceedings{LB94a,
  author = 	 {L\'{e}on Bottou and Corinna Cortes and John S. Denker and
     Harris Drucker and Isabelle Guyon and L.D. Jackel and Yann {LeCun} and Urs A. M\"uller and Eduard S\"ackinger and Patrice Simard
     and Vladimir Vapnik},
  title = 	 {Comparison of classifier methods: a case study in
handwriting digit recognition},
  booktitle = 	 {International Conference on Pattern
     Recognition},
  pages =	 {77--87},
  year =	 {1994}
}

@InProceedings{LB94a-short,
  author = 	 {L\'{e}on Bottou and Corinna Cortes and John S. Denker and
     Harris Drucker and Isabelle Guyon and L.D. Jackel and Yann {LeCun} and Urs A. M\"uller and Eduard S\"ackinger and Patrice Simard
     and Vladimir Vapnik},
  title = 	 {Comparison of classifier methods: a case study in
handwriting digit recognition},
  booktitle = 	 {ICPR},
  pages =	 {77--87},
  year =	 {1994},
}

@INPROCEEDINGS{AB14b,
  author={Bounsiar, Abdenour and Madden, Michael G.},
  booktitle={Proceedings of International Conference on Information Science  Applications (ICISA)}, 
  title={Kernels for One-Class Support Vector Machines}, 
  year={2014},
  volume={},
  number={},
  pages={1--4}
}

@incollection{LB04a,
  author = {L\'{e}on Bottou},
  title = {Stochastic Learning},
  booktitle = {Advanced Lectures on Machine Learning},
  pages = {146--168},
  publisher = {Springer Verlag},
  year = {2004},
  editor = {Bousquet, Olivier and von Luxburg, Ulrike},
  series = {Lecture Notes in Artificial Intelligence, LNAI~3176}
}

@article{LB04b,
 title = {Large Scale Online Learning},
 author = {Bottou, L\'{e}on and {LeCun}, Yann},
 journal = {Advances in Neural Information Processing Systems},
 volume = {16},
 pages = {217--224},
 year = {2004}
}

@incollection{LB07a,
 title = {The Tradeoffs of Large Scale Learning},
 author = {L\'{e}on Bottou and Olivier  Bousquet},
 booktitle = {Advances in Neural Information Processing Systems 20},
 editor = {J.C. Platt and D. Koller and Y. Singer and S. Roweis},
 publisher = {MIT Press},
 address = {Cambridge, MA},
 pages = {},
 year = {2008}
}


@InProceedings{LB07a-short,
  author = {Leon Bottou and Olivier Bousquet},
  title = {The Tradeoffs of Large Scale Learning},
  year = {2007},
  booktitle = {NIPS 21}
}


@incollection{LB07b,
  author = {Bottou, L\'{e}on and Lin, Chih-Jen},
  title = {Support Vector Machine Solvers},
  pages = {1--28},
  editor = {Bottou, L\'{e}on and Chapelle, Olivier and {DeCoste}, Dennis and Weston, Jason},
  booktitle = {Large Scale Kernel Machines},
  publisher = {MIT Press},
  address = {Cambridge, MA.},
  year = {2007},
  url = {http://www.csie.ntu.edu.tw/~cjlin/papers/bottou_lin.pdf}
}

@incollection{LB07b-short,
  author = {Bottou, L\'{e}on and Lin, Chih-Jen},
  title = {Support Vector Machine Solvers},
  booktitle = {Large Scale Kernel Machines},
  year = {2007},
}

@Misc{LB07c,
author = {Leon Bottou},
title = {Stochastic Gradient Descent Examples},
year = {2007},
note = {\url{http://leon.bottou.org/projects/sgd}}
}


@incollection{LB10a,
	title={Large-scale machine learning with stochastic gradient descent},
	author={Bottou, L{\'e}on},
	booktitle={Proceedings of COMPSTAT 2010},
	pages={177--186},
	year={2010}
}

@article{LB13a,
title={Counterfactual reasoning and learning systems: The example of computational advertising},
author={Bottou, L{\'e}on and Peters, Jonas and Qui{\~n}onero-Candela, Joaquin and Charles, Denis X. and Chickering, D. Max and Portugaly, Elon and Ray, Dipankar and Simard, Patrice and Snelson, Ed},
journal={The Journal of Machine Learning Research},
volume={14},
pages={3207--3260},
year={2013}
}

@article{LB13a-short,
title={Counterfactual reasoning and learning systems: The example of computational advertising},
author={Bottou, L{\'e}on and Peters, Jonas and Qui{\~n}onero-Candela, Joaquin and Charles, Denis X. and Chickering, D. Max and Portugaly, Elon and Ray, Dipankar and Simard, Patrice and Snelson, Ed},
journal={JMLR},
volume={14},
pages={3207--3260},
year={2013}
}


@TechReport{AB97,
author      = {Ali Bouaricha and Jorge J. Mor\'e and Zhijun Wu},
title       = {Newton's method for large-scale optimization},
institution = {Argonne National Laboratory},
address     = {Argonne, Illinois},
year        = {1997},
type        = {Preprint},
number      = {MCS-P635-0197},
}

@TechReport{AB97-short,
author      = {Ali Bouaricha and Jorge J. Mor\'e and Zhijun Wu},
title       = {Newton's method for large-scale optimization},
institution = {Argonne National Laboratory},
year        = {1997},
number      = {MCS-P635-0197},
}

@Article{MB04a,
  author =       {Matthew R. Boutell and Jiebo Luo and Xipeng Shen and Christopher M. Brown},
  title =        {Learning multi-label scene classification},
  journal =      {Pattern Recognition},
  year =         {2004},
  OPTkey =       {},
  volume =       {37},
  number =       {9},
  pages =        {1757--1771},
  OPTmonth =     {},
  OPTnote =      {},
  OPTannote =    {}
}


@techreport{MB03a,
  title={{Multi-label semantic scene classification}},
  author =       {Matthew R. Boutell and Jiebo Luo and Xipeng Shen and Christopher M. Brown},
  institution={Technical report, Deptartment of Comuter Science, 
University of Rochester},
  year ={2003}
}


@book{SB04a,
  title = {Convex Optimization},
  author = {Stephen Boyd and Lieven Vandenberghe},
  year = {2004},
  publisher = {Cambridge University Press}
} 


@Article{SB11b,
  author = 	 {S. Boyd and N. Parikh and E. Chu and B. Peleato and J. Eckstein},
  title = 	 {Distributed optimization and statistical
learning via the alternating direction method of multipliers},
  journal = 	 {Foundations and Trends in Machine Learning},
  year = 	 {2011},
  OPTkey = 	 {},
  volume =	 {3},
  number =	 {1},
  pages =	 {1--122}
}

@Article{SB11b-short,
  author = 	 {S. Boyd and N. Parikh and E. Chu and B. Peleato and J. Eckstein},
  title = 	 {Distributed optimization and statistical
learning via the alternating direction method of multipliers},
  journal = 	 {Found. Trends Mach. Learn.},
  year = 	 {2011},
  OPTkey = 	 {},
  volume =	 {3},
  pages =	 {1--122}
}

@inproceedings{JKB11a,
  author = {Joseph K. Bradley and Aapo Kyrola and Danny Bickson and Carlos Guestrin},
  title = {Parallel coordinate descent for l1-regularized loss minimization},
  booktitle = {Proceedings of the Twenty Eighth International
Conference on Machine Learning (ICML)},
  year = {2011},
  pages = {321--328}
}

@inproceedings{JKB11a-short,
  author = {Joseph K. Bradley and Aapo Kyrola and Danny Bickson and Carlos Guestrin},
  title = {Parallel coordinate descent for l1-regularized loss minimization},
  booktitle = {ICML},
  year = {2011}
}


@inproceedings{PSB98a,
  author = {Paul S. Bradley and Olvi
L. Mangasarian},
  title = {Feature Selection via Concave
Minimization and Support Vector Machines},
  booktitle = {Proceedings of the Twenty Fifth
International Conference on Machine Learning
(ICML)},
  year = {1998}
}
%  url = {ftp://ftp.cs.wisc.edu/math-prog/tech-reports/98-03.ps},

@article{PSB00a,
  author = {Bradley, Paul S. and Mangasarian, Olvi L.},
  title = {Massive Data Discrimination via Linear Support Vector Machines},
  journal = {Optimization Methods and Software},
  volume = {13},
  number = {1},
  pages = {1--10},
  year = {2000}
}

@article{RB52a,
author      = {Ralph A. Bradley and Milton E. Terry},
journal     = {Biometrika},
pages       = {324--345},
title       = {The rank analysis of incomplete block designs: I. The
method of paired comparisons},
volume      = {39},
year        = {1952}
}

@Article{RB55a,
  author = 	 {Ralph A. Bradley},
  title = 	 {Rank analysis of incomplete block designs. {III}. {S}ome large-sample results on estimation and power for a method of paired comparisons},
  journal = 	 {Biometrika},
  year = 	 {1955},
  OPTkey = 	 {},
  volume =	 {42},
  OPTnumber = 	 {},
  pages =	 {450--470},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@techreport{JB03a,
  title={Training text classifiers with {SVM} on very few positive examples},
  author={Brank, Janez and Grobelnik, Marko and Mili\'c-Frayling, Nata{\v{s}}a and Mladeni\'c, Dunja},
  year={2003},
  institution={Technical Report MSR-TR-2003-34, Microsoft Corp}
}

@inproceedings{MB15a,
 author = {Braunhofer, Matthias and Ricci, Francesco and Lamche, B{\'e}atrice and W\"{o}rndl, Wolfgang},
 title = {A Context-Aware Model for Proactive Recommender Systems in the Tourism Domain},
 booktitle = {Proceedings of the 17th International Conference on Human-Computer Interaction with Mobile Devices and Services Adjunct (MobileHCI)},
 year = {2015},
 pages = {1070--1075}
}

@inproceedings{MB15a-short,
 author = {Braunhofer, Matthias and Ricci, Francesco and Lamche, B{\'e}atrice and W\"{o}rndl, Wolfgang},
 title = {A Context-Aware Model for Proactive Recommender Systems in the Tourism Domain},
 booktitle = {MobileHCI},
 year = {2015}
}

@Article{EJB99a,
  author = 	 {E. J. Bredensteiner and Kristin P. Bennett},
  title = 	 {Multicategory Classification by Support Vector
     Machines},
  journal = 	 {Computational Optimizations and Applications},
  year = 	 {1999},
  pages =	 {53--79}
}

@inproceedings{KHB10a,
  author={Brodersen, Kay Henning and Ong, Cheng Soon and Stephan, Klaas Enno and Buhmann, Joachim M.},
booktitle = {Proceedings of the 20th International Conference on Pattern Recognition},
  title={The Balanced Accuracy and Its Posterior Distribution}, 
  year={2010},
  volume={},
  number={},
  pages={3121--3124},
}

@inproceedings{JSB98a,
 author = {Breese, John S. and Heckerman, David and Kadie, Carl},
 title = {Empirical Analysis of Predictive Algorithms for
Collaborative Filtering},
 booktitle = {Proceedings of the Fourteenth Conference on Uncertainty
in Artificial Intelligence (UAI)},
 year = {1998},
 pages = {43--52}
}

@inproceedings{JSB98a-short,
 author = {Breese, John S. and Heckerman, David and Kadie, Carl},
 title = {Empirical Analysis of Predictive Algorithms for
Collaborative Filtering},
 booktitle = {UAI},
 year = {1998},
}


@article{LB01a,
    author = "Leo Breiman",
    title = "Random forests",
    journal = "Machine Learning",
    volume = "45",
    number = "1",
    publisher = "Kluwer Academic Publishers, Boston",
    pages = "5--32",
    year = "2001"
}


@article{LB96a,
    author = {Breiman, Leo},
    journal = {Machine Learning},
    month = {August},
    number = {2},
    pages = {123--140},
    publisher = {Springer Netherlands},
    title = {Bagging predictors},
    volume = {24},
    year = {1996}
}



@Article{GWB50a,
  author = 	 {Brier, G. W.},
  title = 	 {Verification of forecasts expressed in probabilities},
  journal = 	 {Monthly Weather Review},
  year = 	 {1950},
  volume =	 {78},
  pages =	 {1--3}
}


@article{DB06a,
    author = {Brizan, David Guy and Tansel, Abdullah Uz},
    journal = {Communications of the IIMA},
    number = {3},
    pages = {41--50},
    title = {A Survey of Entity Resolution and Record Linkage Methodologies},
    volume = {6},
    year = {2006}
}

@book {AB92a,
author      = {Anthony Brooke and David Kendrick and Alexander Meeraus},
title       = {GAMS: {A} user's guide},
publisher   = {Boyd \& Fraser Publishing Company},
year        = {1992},
}		  



@TechReport{MB63a,
   author =       {M. Brown},
   title =        {A Generalized Error Function in N Dimensions},
   year =         {1963},
  OPTkey = 	 {},
  OPTtype = 	 {},
  OPTnumber = 	 {},
  OPTaddress = 	 {},
  OPTmonth = 	 {},
  note =	 {Technical Memorandum No. NMC-TM-63-8, US Naval Missile Center},
  OPTannote = 	 {}
}

@article{MB00a, author =
{M. P. S. Brown and W. N. Grundy and D. Lin and
N. Cristianini and C. Sugnet and T. S. Furey and
M. {Ares, Jr.} and D. Haussler}, 
title =
{Knowledge-based Analysis of Microarray Gene
Expression Data Using Support Vector Machines},
journal = {Proceedings of the National Academy of Science}, 
year = 2000, volume = 97,
number = 1, 
pages = {262--267} }

@inproceedings{TB2020a,
 author = {Brown, Tom and Mann, Benjamin and Ryder, Nick and Subbiah, Melanie and Kaplan, Jared D and Dhariwal, Prafulla and Neelakantan, Arvind and Shyam, Pranav and Sastry, Girish and Askell, Amanda and Agarwal, Sandhini and Herbert-Voss, Ariel and Krueger, Gretchen and Henighan, Tom and Child, Rewon and Ramesh, Aditya and Ziegler, Daniel and Wu, Jeffrey and Winter, Clemens and Hesse, Chris and Chen, Mark and Sigler, Eric and Litwin, Mateusz and Gray, Scott and Chess, Benjamin and Clark, Jack and Berner, Christopher and McCandlish, Sam and Radford, Alec and Sutskever, Ilya and Amodei, Dario},
 booktitle = {Advances in Neural Information Processing Systems},
 editor = {H. Larochelle and M. Ranzato and R. Hadsell and M.F. Balcan and H. Lin},
 pages = {1877--1901},
 publisher = {Curran Associates, Inc.},
 title = {Language Models are Few-Shot Learners},
 volume = {33},
 year = {2020}
}

@article{CGB70a,
    title={The convergence of a class of double-rank minimization
        algorithms 1. general considerations},
    author={Broyden, Charles George},
    journal={IMA Journal of Applied Mathematics},
    volume={6},
    number={1},
    pages={76--90},
    year={1970}
}


		  
@Misc{JPB04a,
  OPTkey = 	 {},
  author =	 {Jean-Philippe Brunet},
  title =	 {\url{http://www.broad.mit.edu/mpr/publications/projects/NMF/nmf.m}},
  OPThowpublished = {},
  OPTmonth = 	 {},
  year =	 {2004},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@Article{JPB04b,
  author = 	 {Jean-Philippe Brunet and Pablo Tamayo and Todd R. Golub and Jill P. Mesirov},
  title = 	 {Metagenes and molecular pattern discovery using matrix factorization},
  journal = 	 {Proceedings of the National Academy of Science},
  year = 	 {2004},
  OPTkey = 	 {},
  volume =	 {101},
  number =	 {12},
  pages =	 {4164--4169},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@techreport{SB15a,
	title={A geometric alternative to {N}esterov's accelerated gradient descent},
	author={Bubeck, S{\'e}bastien and Lee, Yin Tat and Singh, Mohit},
	note={arXiv preprint arXiv:1506.08187},
	year={2015}
}

@article{SB15b,
	title={Convex optimization: Algorithms and complexity},
	author={Bubeck, S{\'e}bastien},
	journal={Foundations and Trends in Machine Learning},
	volume={8},
	number={3-4},
	pages={231--357},
	year={2015}
}

@inproceedings{AB09c,
 author = {Bulu\c{c}, Aydin and Fineman, Jeremy T. and Frigo, Matteo and Gilbert, John R. and Leiserson, Charles E.},
 title = {Parallel Sparse Matrix-vector and Matrix-transpose-vector Multiplication Using Compressed Sparse Blocks},
 booktitle = {Proceedings of the Twenty-first Annual Symposium on Parallelism in Algorithms and Architectures (SPAA)},
 year = {2009},
 pages = {233--244}
} 

@inproceedings{AB09c-short,
 author = {Bulu\c{c}, Aydin and Fineman, Jeremy T. and Frigo, Matteo and Gilbert, John R. and Leiserson, Charles E.},
 title = {Parallel Sparse Matrix-vector and Matrix-transpose-vector Multiplication Using Compressed Sparse Blocks},
 booktitle = {SPAA},
 year = {2009}
} 


@misc{RB02b,
  title={Stopping criteria for {SVM}s},
  author={Burbidge, Robert},
  year={2002},
  howpublished={\url{https://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.18.5021}}
}



@INCOLLECTION{RB91,
        AUTHOR = "R.E. Burkard ",
        TITLE = " Locations with spatial interactions: the quadratic
                    assignment problem",
        booktitle = " Discrete Location Theory",
        publisher = "Wiley",
        editor  =  "P.B.\ Mirchandani and R.L.\ Francis",
        YEAR = 1991,
        }


@TechReport{RB96,
author      = {R.E. Burkard and S.E. Karisch and F. Rendl},
address     = {Graz, Austria},
institution = {Department of Mathematics, Graz University of Technology},
title       = {{QAPLIB} - A Quadratic Assignment Problem Library},
year        = {1996}
}

@article{JVB88,
author      = {J. V. Burke and J. J. Mor\'e},
journal     = {SIAM J. Numer. Anal.},
pages       = {1197--1211},
title       = {On the identification of active constraints},
volume      = {25},
year        = {1988}
}

@article{JVB90,
author      = {J. V. Burke and J. J. Mor\'e and G. Toraldo},
journal     = {Math. Programming},
pages       = {305--336},
title       = {Convergence properties of trust region methods for linear
and convex constraints},
volume      = {47},
year        = {1990}
}

@article{JVB92,
author      = {J. V. Burke and J. J. Mor\'e},
title       = {Exposing constraints},
journal     = {SIAM J. Optim.},
pages       = {573--595},
volume      = {4},
year        = {1994}
}

@book{CL50a,
title={An iteration method for the solution of the eigenvalue problem of linear differential and integral operators},
author={Lanczos, Cornelius},
year={1950},
publisher={United States Governm. Press Office}
}

@Article{CJCB98a,
  author = 	 "C. J. C. Burges",
  title = 	 "A tutorial on support vector machines for pattern
     recognition",
  journal =	 "Data Mining and Knowledge Discovery",
  year =	 "1998",
  volume =	 "2",
  number =	 "2",
  pages = {121--167}
}

@InProceedings{CJCB99a,
  author = 	 {C. J. C. Burges and D. J. Crisp},
  title = 	 {Uniquness of the {SVM} solution},
  booktitle = 	 {{NIPS}99},
  year =	 {1999}
}


@InProceedings{CJCB99b,
AUTHOR = "C. J. C. Burges",
TITLE = "Geometry and Invariance in Kernel Based Methods",
BOOKTITLE = "Advances in Kernel Methods: Support Vector Learning",
EDITOR = "B. Sch{\"o}lkopf and C.J.C. Burges and A.J. Smola",
PUBLISHER = "MIT Press",
YEAR = "1999",
PAGES = "89--116"
}

@incollection{CJCB07a,
 author = {Christopher J. C. Burges and Robert Ragno and Quoc Viet Le},
 title = {Learning to Rank with Nonsmooth Cost Functions},
 booktitle = {Advances in Neural Information Processing Systems 19},
 editor = {B. Sch\"{o}lkopf and J. Platt and T. Hoffman},
 publisher = {MIT Press},
 address = {Cambridge, MA},
 pages = {193--200},
 year = {2007}
}

@techreport{CJCB10a,
 author={Christopher J. C. Burges},
 title={From {R}ank{N}et to {L}ambda{R}ank to {L}ambda{MART}: An Overview},
 institution = {Microsoft Research},
 year        = {2010},
 number      = {MSR-TR-2010-82},
}

@misc{RBF19a,
      title={On the computational complexity of the probabilistic label tree algorithms},
      author={Robert Busa-Fekete and Krzysztof Dembczynski and Alexander Golovnev and Kalina Jasinska and Mikhail Kuznetsov and Maxim Sviridenko and Chao Xu},
      year={2019},
      eprint={1906.00294},
      archivePrefix={arXiv},
      primaryClass={cs.LG}
}

@article{RHB94,
  author = {Richard H. Byrd and Peihung Lu and Jorge Nocedal and Ciyou Zhu},
  title = {A limited memory algorithm for bound constrained optimization},
  journal = {SIAM Journal on Scientific Computing},
  pages = {1190--1208},
  volume = {16},
  year = {1995}
}

@article{RHB94-short,
  author = {Richard H. Byrd and Peihung Lu and Jorge Nocedal and Ciyou Zhu},
  title = {A limited memory algorithm for bound constrained optimization},
  journal={SIAM J. Sci. Comput.},
  pages = {1190--1208},
  volume = {16},
  year = {1995}
}

@techreport{RHB94a,
author      = {Ciyou Zhu and Richard H. Byrd and Peihung Lu and 
               Jorge Nocedal},
title       = {{L-BFGS-B}: Fortran subroutines for large-scale 
               bound constrained optimization},
institution = {Northwestern University},
year        = {1994},
type        = {{T}echnical {R}eport},
}


@article{RHB94b,
	title={Representations of quasi-{N}ewton matrices and their use in limited memory methods},
	author={Byrd, Richard H. and Nocedal, Jorge and Schnabel, Robert B.},
	journal={Mathematical Programming},
	volume={63},
	number={1},
	pages={129--156},
	year={1994}
}

@article{RHB94b-short,
	title={Representations of quasi-{N}ewton matrices and their use in limited memory methods},
	author={Byrd, Richard H. and Nocedal, Jorge and Schnabel, Robert B.},
	journal={Math. Program.},
	volume={63},
	pages={129--156},
	year={1994}
}

@article{RHB11a,
  title={On the use of stochastic {H}essian information in optimization methods for machine learning},
  author={Richard H. Byrd and Gillian M. Chin and Will Neveitt and Jorge Nocedal},
  journal={SIAM Journal on Optimization},
  volume={21},
  number={3},
  pages={977--995},
  year={2011}
}

@article{RHB11a-short,
  title={On the use of stochastic {H}essian information in optimization methods for machine learning},
  author={Richard H. Byrd and Gillian M. Chin and Will Neveitt and Jorge Nocedal},
  journal={SIAM J. Optim.},
  volume={21},
  number={3},
  pages={977--995},
  year={2011}
}

@Article{RHB12a,
    author="Byrd, Richard H.  and Chin, Gillian M.  and Nocedal, Jorge and Wu, Yuchen",
    title="Sample size selection in optimization methods for machine learning",
    journal="Mathematical Programming",
    year="2012",
    volume="134",
    number="1",
    pages="127--155",
}

@article{RHB16a,
	title={A stochastic quasi-{N}ewton method for large-scale
		optimization},
	author={Byrd, Richard H and Hansen, Samantha L. and Nocedal,
		Jorge and Singer, Yoram},
	journal={{SIAM} Journal on Optimization},
	volume={26},
	number={2},
	pages={1008--1031},
	year={2016}
}

@techreport{JHB12a,
    Author = {Byun, Jong-Ho and Lin, Richard and Yelick, Katherine A. and Demmel, James},
    Title = {Autotuning Sparse Matrix-Vector Multiplication for Multicore},
    Institution = {EECS Department, University of California, Berkeley},
    Year = {2012},
    URL = {http://www.eecs.berkeley.edu/Pubs/TechRpts/2012/EECS-2012-215.html}
}

@techreport{JHB12a-short,
    Author = {Byun, Jong-Ho and Lin, Richard and Yelick, Katherine A. and Demmel, James},
    Title = {Autotuning Sparse Matrix-Vector Multiplication for Multicore},
    Institution = {EECS, UC Berkeley},
    Year = {2012}
}


@inproceedings{TWC94a,
    author = "Timothy W. Cacciatore and Steven J. Nowlan",
    title = "Mixtures of Controllers for Jump Linear and Non-Linear Plants",
    booktitle = "Advances in Neural Information Processing Systems",
    volume = "6",
    publisher = "Morgan Kaufmann Publishers, Inc.",
    editor = "Jack D. Cowan and Gerald Tesauro and Joshua Alspector",
    pages = "719--726",
    year = "1994",
    url = "citeseer.nj.nec.com/51856.html" 
}


@inproceedings{LC04a,
 author = {Lijuan Cai and Thomas Hofmann},
 title = {Hierarchical document categorization with support vector machines},
 booktitle = {CIKM '04: Proceedings of the Thirteenth ACM conference on Information and knowledge management},
 year = {2004},
 isbn = {1-58113-874-1},
 pages = {78--87},
 location = {Washington, D.C., USA},
 doi = {http://doi.acm.org/10.1145/1031171.1031186},
 publisher = {ACM Press},
 }

@inproceedings{LC04a-short,
 author = {Lijuan Cai and Thomas Hofmann},
 title = {Hierarchical document categorization with support vector machines},
 booktitle = {CIKM},
 year = {2004}
 }

@article{WC19a,
title={Neighborhood-enhanced transfer learning for one-class collaborative filtering},
author={Cai, Wanling and Zheng, Jiongbin and Pan, Weike and Lin, Jing and Li, Lin and Chen, Li and Peng, Xiaogang and Ming, Zhong},
journal={Neurocomputing},
volume={341},
pages={80--87},
year={2019}
}

@article{PHC87,
author      = {Paul H. Calamai and Jorge J. Mor\'e},
journal     = {Mathematical Programming},
pages       = {93--116},
title       = {Projected gradient methods for linearly constrained problems},
volume      = {39},
year        = {1987}
}

@article{AC18a,
	title={An adaptive truncation criterion, for linesearch-based truncated {N}ewton methods in large scale nonconvex optimization},
	author={Caliciotti, Andrea and Fasano, Giovanni and Nash, Stephen G. and Roma, Massimo},
	journal={Operations Research Letters},
	volume={46},
	number={1},
	pages={7--12},
	year={2018}
}

@article{AC18a-short,
	title={An adaptive truncation criterion, for linesearch-based truncated {N}ewton methods in large scale nonconvex optimization},
	author={Caliciotti, Andrea and Fasano, Giovanni and Nash, Stephen G. and Roma, Massimo},
        journal = 	 {Oper. Res. Lett.},		
	volume={46},
	pages={7--12},
	year={2018}
}

@inproceedings{PC20a,
    title = "{H}yper{C}ore: Hyperbolic and Co-graph Representation for Automatic {ICD} Coding",
    author = "Cao, Pengfei  and
      Chen, Yubo  and
      Liu, Kang  and
      Zhao, Jun  and
      Liu, Shengping  and
      Chong, Weifeng",
    booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL)",
    year = "2020",
    doi = "10.18653/v1/2020.acl-main.282",
    pages = "3105--3114",
}

@inproceedings{PC20b,
    title = "Clinical-Coder: Assigning Interpretable {ICD}-10 Codes to {C}hinese Clinical Notes",
    author = "Cao, Pengfei  and
      Yan, Chenwei  and
      Fu, Xiangling  and
      Chen, Yubo  and
      Liu, Kang  and
      Zhao, Jun  and
      Liu, Shengping  and
      Chong, Weifeng",
    booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations",
    year = "2020",
    doi = "10.18653/v1/2020.acl-demos.33",
    pages = "294--301",
}

@techreport{HC95a,
author      = {Henri Casanova and Jack Dongarra},
address     = {Knoxville, Tennessee},
institution = {University of Tennessee},
number      = {CS-95-313},
title       = {{NetSolve}: {A} network server for solving computational
               science problems},
type        = {Technical Report},
year        = {1995}
}


@inproceedings{BC08a,
   author = {B. Catanzaro and N. Sundaram and K. Keutzer},
   title = {Fast support vector machine training and classification on graphics processors},
   booktitle = {Proceedings of the Twenty Fifth International Conference on Machine Learning (ICML)},
   year = {2008}
}


@article{MC04b,
  title={{On reduced rank nonnegative matrix factorization for symmetric nonnegative matrices}},
  author={Catral, M. and Han, L. and Neumann, M. and Plemmons, RJ},
  journal={Linear Algebra and Its Applications},
  volume={393},
  pages={107--126},
  year={2004},
  publisher={Elsevier}
}

@inbook{SC17a,
author = {Cavallari, Sandro and Zheng, Vincent W. and Cai, Hongyun and Chang, Kevin Chen-Chuan and Cambria, Erik},
title = {Learning Community Embedding with Community Detection and Node Embedding on Graphs},
year = {2017},
booktitle = {Proceedings of the 2017 ACM on Conference on Information and Knowledge Management (CIKM)},
pages = {377–386}
}

@ARTICLE{SC19a,
  author={Cavallari, Sandro and Cambria, Erik and Cai, Hongyun and Chang, Kevin Chen-Chuan and Zheng, Vincent W.},
  journal={IEEE Computational Intelligence Magazine}, 
  title={Embedding Both Finite and Infinite Communities on Graphs}, 
  year={2019},
  volume={14},
  pages={39--50}
}


@incollection{NC04a,
author = {Nicol\`o Cesa-Bianchi and Claudio Gentile and Andrea Tironi and Luca Zaniboni},
title = {Incremental Algorithms for Hierarchical Classification},
booktitle = "Advances in Neural Information Processing Systems 17",
editor = "Lawrence K. Saul and Yair Weiss and {L\'{e}on} Bottou",
publisher = "MIT Press",
address = "Cambridge, MA",
year = "2005",
}

@InProceedings{NC04a-short,
  author = {Nicol\'o Cesa-Bianchi and Claudio Gentile and Andrea Tironi and
Luca Zaniboni},
  title = {Incremental Algorithms for Hierarchical Classification},
  year = {2005},
  booktitle = {NIPS 17}
}


@InProceedings{Campbell00a,
  author = 	 {Colin Campbell},
  title = 	 {An introduction to kernel methods},
  booktitle = 	 {Radial basis function networks: design and applications},
  year =	 {2000},
  editor =	 {R. J. Howlett and L. C. Jain},
  address =	 {Berlin},
  publisher =	 {Springer Verlag}
}

@article{NC03a,
  title={{Kernel methods for document filtering}},
  author={Cancedda, N. and Cesa-Bianchi, N. and Conconi, A. and Gentile, C. and Goutte, C. and Li, Y. and Renders, J.M. and Shawe-Taylor, J. and Vinokourov, A.},
  journal={Proceedings of The Eleventh Text Retrieval Conference (TREC 2002). The NIST},
  year={2003}
}


@mastersthesis{EC97a,
author      = {E. Carr},
address     = {Waterloo, Ontario, Canada},
school      = {Department of Computer Science, University of Waterloo},
title       = {Preconditioning and performance issues for the solution 
               of ill-conditioned three-dimensional structural
                  analysis problems},
year        = {1997}
}


@incollection{GC01a,
	title={Incremental and decremental support vector machine learning},
	author={Cauwenberghs, Gert and Poggio, Tomaso},
	booktitle={Advances in Neural Information Processing Systems},
	pages={409--415},
	year={2001}
}

@incollection{GC01a-short,
	title={Incremental and decremental support vector machine learning},
	author={Cauwenberghs, Gert and Poggio, Tomaso},
	booktitle={NIPS},
	year={2001}
}

@misc{YC21a,
      title={Cog{DL}: Toolkit for Deep Learning on Graphs}, 
      author={Yukuo Cen and Zhenyu Hou and Yan Wang and Qibin Chen and Yizhen Luo and Xingcheng Yao and Aohan Zeng and Shiguang Guo and Yang Yang and Peng Zhang and Guohao Dai and Yu Wang and Chang Zhou and Hongxia Yang and Jie Tang},
      year={2021},
      eprint={2103.00959},
      archivePrefix={arXiv},
      primaryClass={cs.SI}
}

@conference{HC06a,
  title={Learning Factors Analysis -- A General Method for Cognitive Model Evaluation and Improvement},
  author={Hao Cen and Kenneth Koedinger and Brian Junker},
  booktitle={the 8th International Conference on Intelligent Tutoring Systems},
  year={2006}
}


@book{YC98a,
 author = {Yair Censor and Stavros A. Zenios},
 title = {Parallel Optimization: Theory, Algorithms, and Applications},
 publisher = {Oxford University Press},
 year = {1998}
}

@InProceedings{HC12b,
    booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
	author			= {Cevikalp, Hakan and Triggs, Bill},
	title			= {Efficient object detection using cascades of nearest convex model classifiers},
	pages			= {3138--3145},
	year			= {2012}
}

@inproceedings{DC08a,
 author = {Chakrabarti, Deepayan and Agarwal, Deepak and Josifovski, Vanja},
 title = {Contextual advertising by combining relevance with click feedback},
 booktitle = {Proceeding of the 17th international conference on World
Wide Web},
 year = {2008},
 pages = {417--426}
}

@inproceedings{IC19a,
    title = "Large-Scale Multi-Label Text Classification on {EU} Legislation",
    author = "Chalkidis, Ilias  and
      Fergadiotis, Emmanouil  and
      Malakasiotis, Prodromos  and
      Androutsopoulos, Ion",
    booktitle = "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL)",
    year = "2019",
    doi = "10.18653/v1/P19-1636",
    pages = "6314--6322"
}

@inproceedings{IC19a-short,
    title = "Large-Scale Multi-Label Text Classification on {EU} Legislation",
    author = "Chalkidis, Ilias  and
      Fergadiotis, Emmanouil  and
      Malakasiotis, Prodromos  and
      Androutsopoulos, Ion",
    booktitle = "ACL",
    year = "2019",
}

@inproceedings{IC19b,
    title = "Neural Legal Judgment Prediction in {E}nglish",
    author = "Chalkidis, Ilias  and
      Androutsopoulos, Ion  and
      Aletras, Nikolaos",
    editor = "Korhonen, Anna  and
      Traum, David  and
      M{\`a}rquez, Llu{\'\i}s",
    booktitle = "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics",
    year = "2019",
    doi = "10.18653/v1/P19-1424",
    pages = "4317--4323",
}

@inproceedings{IC20a,
    title = "An Empirical Study on Large-Scale Multi-Label Text Classification Including Few and Zero-Shot Labels",
    author = "Chalkidis, Ilias  and
      Fergadiotis, Manos  and
      Kotitsas, Sotiris  and
      Malakasiotis, Prodromos  and
      Aletras, Nikolaos  and
      Androutsopoulos, Ion",
    booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
    year = "2020",
    doi = "10.18653/v1/2020.emnlp-main.607",
    pages = "7503--7515"
}

@inproceedings{IC20a-short,
    title = "An Empirical Study on Large-Scale Multi-Label Text Classification Including Few and Zero-Shot Labels",
    author = "Chalkidis, Ilias  and
      Fergadiotis, Manos  and
      Kotitsas, Sotiris  and
      Malakasiotis, Prodromos  and
      Aletras, Nikolaos  and
      Androutsopoulos, Ion",
    booktitle = "EMNLP",
    year = "2020"
}

@inproceedings{IC21a,
    title = "Paragraph-level Rationale Extraction through Regularization: A case study on {E}uropean Court of Human Rights Cases",
    author = "Chalkidis, Ilias  and
      Fergadiotis, Manos  and
      Tsarapatsanis, Dimitrios  and
      Aletras, Nikolaos  and
      Androutsopoulos, Ion  and
      Malakasiotis, Prodromos",
    editor = "Toutanova, Kristina  and
      Rumshisky, Anna  and
      Zettlemoyer, Luke  and
      Hakkani-Tur, Dilek  and
      Beltagy, Iz  and
      Bethard, Steven  and
      Cotterell, Ryan  and
      Chakraborty, Tanmoy  and
      Zhou, Yichao",
    booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
    year = "2021",
    doi = "10.18653/v1/2021.naacl-main.22",
    pages = "226--241",
}

@inproceedings{IC21b,
    title = "{M}ulti{EURLEX} - A multi-lingual and multi-label legal document classification dataset for zero-shot cross-lingual transfer",
    author = "Chalkidis, Ilias  and
      Fergadiotis, Manos  and
      Androutsopoulos, Ion",
    editor = "Moens, Marie-Francine  and
      Huang, Xuanjing  and
      Specia, Lucia  and
      Yih, Scott Wen-tau",
    booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
    year = "2021",
    address = "Online and Punta Cana, Dominican Republic",
    doi = "10.18653/v1/2021.emnlp-main.559",
    pages = "6974--6996",
}

@article{IC22a,
  author  = {Ines Chami and Sami Abu-El-Haija and Bryan Perozzi and Christopher R{\'e} and Kevin Murphy},
  title   = {Machine Learning on Graphs: A Model and Comprehensive Taxonomy},
  journal = {Journal of Machine Learning Research},
  year    = {2022},
  volume  = {23},
  number  = {89},
  pages   = {1--64}
}

@inproceedings{IC22b,
    title = "{L}ex{GLUE}: A Benchmark Dataset for Legal Language Understanding in {E}nglish",
    author = "Chalkidis, Ilias  and
      Jana, Abhik  and
      Hartung, Dirk  and
      Bommarito, Michael  and
      Androutsopoulos, Ion  and
      Katz, Daniel  and
      Aletras, Nikolaos",
    booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics",
    year = "2022",
    pages = "4310--4330"
}

@article{JC04a,
  author = {John-Marc Chandonia and Gary Hon and Nigel S. Walker and
Loredana Lo Conte and Patrice Koehl and Michael Levitt and Steven E.
Brenner},
  title = {The ASTRAL Compendium in 2004},
  journal = {Nucleic Acids Research},
  year = {2004},
  volume = {32},
  pages = {D189--D192}
}

@inproceedings{DKC19a,
  title={Collective representation learning on spatiotemporal heterogeneous information networks},
  author={Chandra, Dakshak Keerthi and Wang, Pengyang and Leopold, Jennifer and Fu, Yanjie},
  booktitle={Proceedings of the 27th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems},
  pages={319--328},
  year={2019}
}

@techreport{CCC07a,
	author = {Chien-Chung Chang and Hsi-Chen Tsai and Yuh-Jye Lee},
	title = {A Minimum Enclosing Balls Labeling Method for Support Vector Clustering},
	institution = {National Taiwan University of Science and Technology},
	year = {2007},
	url = {http://dmlab8.csie.ntust.edu.tw/downloads/papers/SVC_MEB.pdf}
}

@InProceedings{CCC99a,
  author = 	 {Chih-Chung Chang and Chih-Wei Hsu and Chih-Jen Lin},
  title = 	 {The Analysis of Decomposition Methods for Support
Vector Machines},
  booktitle = 	 {Workshop on {S}upport {V}ector {M}achines, {IJCAI}99},
  year =	 {1999}
}

@Article{CC00b,
  author = 	 {Chih-Chung Chang and Chih-Wei Hsu and Chih-Jen Lin},
  title = 	 {The Analysis of Decomposition Methods for Support
Vector Machines},
  year =	 {2000},
  volume=        {11},
  number=        {4},
  pages=         {1003--1008},
  journal = 	 {IEEE Transactions on  Neural Networks}
}

@TechReport{CC00c,
  author = 	 {Chih-Chung Chang and Chih-Jen Lin},
  title = 	 {{LIBSVM}: Introduction
and Benchmarks},
  institution =  {Department of Computer Science and
Information Engineering,
National Taiwan University,
Taipei, Taiwan
},
  year = 	 {2000}
}


@TechReport{CC00d,
  author = 	 {Chih-Chung Chang and Chih-Jen Lin},
  title = 	 {An Integrated Implementation 
for Support Vector Classification 
and Regression},
  institution =  {Department of Computer Science and
Information Engineering,
National Taiwan University,
Taipei, Taiwan
},
  year = 	 {2000},
  note = {In Preparation}
}

@Misc{CC00e,
  author =	 {Chih-Chung Chang and Chih-Jen Lin},
  title =	 {{LIBSVM} 2.0:
Solving Different
Support Vector Formulations},
  year =	 {2000},
  note =	 {Software available at {\tt http://www.csie.ntu.edu.tw/\verb"~"cjlin/libsvm}},
}


@article{CC01a,
 author = {Chang, Chih-Chung and Lin, Chih-Jen},
 title = {{LIBSVM}: a library for support vector machines},
 journal = {ACM Transactions on Intelligent Systems and Technology},
 volume = {2},
 number = {3},
 year = {2011},
 pages = {27:1--27:27},
 note =	 {Software available at \url{http://www.csie.ntu.edu.tw/~cjlin/libsvm}}
}

@Manual{CC01a-old,
  author =	 {Chih-Chung Chang and Chih-Jen Lin},
  title =	 {{LIBSVM}: a library for support vector machines},
  year =	 {2001},
  note =	 {Software available at \url{http://www.csie.ntu.edu.tw/~cjlin/libsvm}}
}
%  url = {http://www.csie.ntu.edu.tw/~cjlin/papers/libsvm.pdf}

@article{CC01a-short,
 author =	{C.-C. Chang and C.-J. Lin},
 title = {{LIBSVM}: A library for support vector machines},
 journal = {ACM TIST},
 volume = {2},
 number = {3},
 year = {2011},
 pages = {27:1--27:27}
}


@Article{CC01b,
  author = 	 {Chih-Chung Chang and Chih-Jen Lin},
  title = 	 {Training $\nu$-Support Vector Classifiers: Theory and Algorithms},
  year = 	 {2001},
  journal = {Neural Computation},
  volume = {13},
  number ={9},
  pages       = {2119--2147}
}


@Article{CC01c,
  author = 	 {Chih-Chung Chang and Chih-Jen Lin},
  title = 	 {Training
$\nu$-Support Vector Regression:
Theory and Algorithms},
   journal={Neural Computation},
volume={14},
number={8},
pages={1959--1977},
  year = 	 {2002}
}


@InProceedings{Chang01d,
  author = 	 {Chih-Chung Chang and
Chih-Jen Lin},
  title = 	 {{IJCNN} 2001 Challenge: Generalization Ability and 
Text Decoding},
  booktitle = 	 {Proceedings of IJCNN},
  publisher={IEEE},
  year =	 {2001}
}

@mastersthesis{CC01e,
author      = {Chih-Chung Chang},
school      = {Department of Computer Science and Information Engineering,
National Taiwan University},
title       = {Study on New Support Vector Machines},
year        = {2001}
}


@INPROCEEDINGS{CYC20a,
  author={Chih-Yao Chang and Xing Tang and Bowen Yuan and Jui-Yang Hsia and Zhirong Liu and Zhenhua Dong and Xiuqiang He and Chih-Jen Lin},
  booktitle={Proceedings of the 21st IEEE International Conference on Mobile Data Management (MDM)}, 
  title={Auto{C}onjunction: adaptive model-based feature conjunction for {CTR} prediction}, 
  year={2020},
  volume={},
  number={},
  pages={202-209},}

@incollection{EC07a,
 title = {Parallelizing Support Vector Machines on Distributed Computers},
 author = {Edward Chang and Kaihua Zhu and Hao Wang and Hongjie Bai
and Jian Li and Zhihuan Qiu and Hang Cui},
 booktitle = {Advances in Neural Information Processing Systems 20},
 editor = {J.C. Platt and D. Koller and Y. Singer and S. Roweis},
 publisher = {MIT Press},
 address = {Cambridge, MA},
 pages = {257--264},
 year = {2008}
}


@InProceedings{EC07a-short,
  author = {Edward Chang and  Kaihua Zhu and  Hao Wang and  Hingjie Bai and  Jian Li and  Zhihuan Qiu and  Hang Cui},
  title = {Parallelizing Support Vector Machines on Distributed Computers},
  year = {2007},
  booktitle = {NIPS 21}
}

@Book{EYC11a,
  author =      {Edward Y. Chang},
  title =        {Foundations of Large-Scale Multimedia Information Management and Retrieval},
  publisher =    {Springer-Verlag New York Inc},
  year =        {2011},
  address =     {New York}
}

@Article{KWC07a,
author = {Kai-Wei Chang and Cho-Jui Hsieh and Chih-Jen Lin},
title = {Coordinate Descent Method for Large-scale {L}2-loss Linear {SVM}},
  journal = 	 {Journal of Machine Learning Research},
  url = {http://www.csie.ntu.edu.tw/~cjlin/papers/cdl2.pdf},
  year =     {2008},
  pages={1369--1398},
  volume={9},
  OPTkey =   {},
  OPTtype =      {},
  OPTnumber =    {},
  OPTaddress =   {},
  OPTmonth =     {},
  OPTnote =      {},
  OPTannote =    {}
}
%  institution =  {National Taiwan University},

@Article{KWC07a-short,
author = {Chang, K.-W. and Hsieh, C.-J. and Lin, C.-J.},
title = {Coordinate Descent Method for Large-scale {L}2-loss Linear {SVM}},
  journal =      {JMLR},
  year =     {2008},
  pages={1369--1398},
  volume={9},
  OPTkey =   {},
  OPTtype =      {},
  OPTnumber =    {},
  OPTaddress =   {},
  OPTmonth =     {},
  OPTnote =      {},
  OPTannote =    {}
}

@inproceedings{KWC11a,
 author = {Kai-Wei Chang and Dan Roth},
 title = {Selective Block Minimization for Faster Convergence of
Limited Memory Large-scale Linear Models},
 booktitle = {Proceedings of the Seventeenth ACM SIGKDD International
Conference on Knowledge Discovery and Data Mining},
 year = {2011}
}


@InProceedings{MWC01a,
  author = 	 {Ming-Wei Chang and Bo-Juen Chen and Chih-Jen Lin},
  title = 	 {{EUNITE} Network Competition:
Electricity Load Forecasting},
  year =	 {2002},
  note =	 {Winner of {EUNITE} world wide 
competition on electricity load prediction
}
}

@InProceedings{MWC02a,
  author = 	 {Ming-Wei Chang and   Chih-Jen Lin and Ruby C. Weng},
  title = 	 {Analysis of switching dynamics with
competing support vector machines
},
  year =	 {2002},
  booktitle = 	 {Proceedings of IJCNN},
  pages={2387--2392}  
}


@Article{MWC02b,
  author = 	 {Ming-Wei Chang and   Chih-Jen Lin and Ruby C. Weng},
  title = 	 {Analysis of switching dynamics with competing support vector machines},
  pages={720--727},
  volume={15},
  number={3},
  year =	 {2004},
  journal =	 {IEEE Transactions on Neural Networks}
}

@InProceedings{MWC02c,
  author = 	 {Ming-Wei Chang and   Chih-Jen Lin and Ruby C. Weng},
  title = 	 {Analysis of nonstationary time series using
support vector machines},
  year =	 {2002},
  booktitle = 	 {Proceedings of SVM 2002},  
  pages =	 {160--170},
  editor =	 {Seong-Whan Lee and Alessandro Verri},
  series =	 {Lecture Notes in Computer Science 2388},
  publisher =	 {Springer-Verlag Inc.},
  address ={New York, NY, USA}
}

%  booktitle = 	 {Proceedings of International workshop on pattern recognition with support vector machines (SVM 2002)}  


@TechReport{MWC02d,
  author = 	 {Ming-Wei Chang and   Chih-Jen Lin and Ruby C. Weng},
  title = 	 {Analysis of nonstationary time series using support vector machines},
  institution =  {Department of Computer Science and
Information Engineering, 
National Taiwan University},
  year =	 {2002}
}



@InProceedings{MWC02e,
  author = 	 {Ming-Wei Chang and   Chih-Jen Lin and Ruby C. Weng},
  title = 	 {Adaptive deterministic annealing for two applications:
competing {SVR} of switching dynamics and travelling salesman
problems},
  booktitle = 	 {Proceedings of ICONIP 2002},
  pages = {920--924},
  year =	 {2002}
}

@Article{MWC03a,
  author = 	 {Ming-Wei Chang and Chih-Jen Lin},
  title = 	 {Leave-one-out Bounds for Support Vector Regression Model Selection},
  journal = {Neural Computation},
  volume={17},
  number={5},
  pages={1188--1222},
  year =	 {2005}
}

@inproceedings{MWC10a,
  author = {Ming-Wei Chang and Vivek Srikumar and Dan Goldwasser and Dan Roth},
  title = {Structured Output Learning with Indirect Supervision},
  booktitle = {Proceedings of the Twenty Seven International Conference on Machine Learning (ICML)},
  pages = {199--206},
  year = {2010}
}

@techreport{WCC13a,
author      = "Wei-Cheng Chang and Ching-Pei Lee and Chih-Jen Lin",
title       = "A Revisit to Support Vector Data Description",
year        = "2013",
url={http://www.csie.ntu.edu.tw/~cjlin/papers/svdd.pdf}
}

@inproceedings{WCC20a,
  title={Taming pretrained transformers for extreme multi-label text classification},
  author={Chang, Wei-Cheng and Yu, Hsiang-Fu and Zhong, Kai and Yang, Yiming and Dhillon, Inderjit S.},
  booktitle={Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)},
  pages={3163--3171},
  year={2020}
}

@inproceedings{WCC20a-short,
  title={Taming pretrained transformers for extreme multi-label text classification},
  author={Chang, Wei-Cheng and Yu, Hsiang-Fu and Zhong, Kai and Yang, Yiming and Dhillon, Inderjit S.},
  booktitle={KDD},
  year={2020}
}

@inproceedings{WCC21a,
	title={Extreme multi-label learning for semantic matching in product search},
	author={Chang, Wei-Cheng and Jiang, Daniel and Yu, Hsiang-Fu and Teo, Choon-Hui and Zhang, Jiong and Zhong, Kai and Kolluri, Kedarnath and Hu, Qie and Shandilya, Nikhil and Ievgrafov, Vyacheslav and Singh, Japinder and Dhillon, Inderjit S},
	booktitle={Proceedings of the 27th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)},
	year={2021}
}

@InProceedings{YWC08a,
  author = 	 {Yin-Wen Chang and Chih-Jen Lin},
  title = 	 {Feature Ranking Using Linear {SVM}},
  booktitle = 	 {JMLR Workshop and Conference Proceedings: Causation and Prediction Challenge (WCCI 2008)},
  OPTcrossref =  {},
  OPTkey = 	 {},
  pages =	 {53--64},
  year =	 {2008},
  OPTeditor = 	 {},
  volume =	 {3},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTaddress = 	 {},
  OPTmonth = 	 {},
  OPTorganization = {},
  OPTpublisher = {},
  OPTnote = 	 {},
  OPTannote = 	 {},
  url = {http://www.csie.ntu.edu.tw/~cjlin/papers/causality.pdf}
}



@Article{YWC09a,
  author = 	 {Yin-Wen Chang and Cho-Jui Hsieh and Kai-Wei Chang and Michael Ringgaard and Chih-Jen Lin},
  title = 	 {Training and Testing Low-degree Polynomial Data Mappings via Linear {SVM}},
  journal   = {Journal of Machine Learning Research},
  year      = {2010},
  pages     = {1471--1490},
  volume    = {11},
  url =	 {http://www.csie.ntu.edu.tw/~cjlin/papers/lowpoly_journal.pdf}
}

@Article{YWC09a-short,
  author = 	 {Yin-Wen Chang and Cho-Jui Hsieh and Kai-Wei Chang and Michael Ringgaard and Chih-Jen Lin},
  title = 	 {Training and Testing Low-degree Polynomial Data Mappings via Linear {SVM}},
  journal   = {JMLR},
  year      = {2010},
  pages     = {1471--1490},
  volume    = {11}
}

@inproceedings{SC20a,
author = {Chanpuriya, Sudhanshu and Musco, Cameron},
title = {{I}nfinite{W}alk: Deep Network Embeddings as {L}aplacian Embeddings with a Nonlinearity},
year = {2020},
booktitle = {Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)},
pages = {1325–1333}
}

@InProceedings{SC21a,
  title = 	 {DeepWalking Backwards: From Embeddings Back to Graphs},
  author =       {Chanpuriya, Sudhanshu and Musco, Cameron and Sotiropoulos, Konstantinos and Tsourakakis, Charalampos},
  booktitle = 	 {Proceedings of the 38th International Conference on Machine Learning (ICML)},
  pages = 	 {1473--1483},
  year = 	 {2021}
}

@InProceedings{Chapelle00a,
  author        = {O. Chapelle and V. Vapnik},
  title         = {Model Selection for Support Vector Machines},
  booktitle     = {Advances in Neural Information Processing Systems 12},
  year          = {2000},
  editor        = {Sara A. Solla and Todd K. Leen and Klaus-Robert M{\"u}ller},
  publisher     = {Cambridge, Mass: MIT Press},
  url           = {http://www.ens-lyon.fr/{\~}ochapell/ms_nips99.ps}
}
    
@Article{Chapelle00b,
  author = 	 {O. Chapelle and V. Vapnik and O. Bousquet and S. Mukherjee},
  title = 	 {Choosing Multiple Parameters for
     Support Vector Machines},
  year = 	 {2002},
  pages={131--159},
  volume={46},
  journal =	 {Machine Learning}
}

@Article{Chapelle00b-short,
  author = 	 {O. Chapelle and V. Vapnik and O. Bousquet and S. Mukherjee},
  title = 	 {Choosing Multiple Parameters for
     Support Vector Machines},
  year = 	 {2002},
  pages={131--159},
  volume={46},
  journal =	 {MLJ}
}

@article{OC07a,
        author = {Olivier Chapelle},
        title = {Training a Support Vector Machine in the Primal},
        journal = {Neural Computation},
        volume = {19},
        number = {5},
        year = {2007},
        pages = {1155--1178}
}

@article{OC07a-short,
        author = {Olivier Chapelle},
        title = {Training a Support Vector Machine in the Primal},
 journal     ={Neural Comput.},
        volume = {19},
        year = {2007},
        pages = {1155--1178}
}

@article{OC10a,
 author={Chapelle, Olivier and Keerthi, S. Sathiya},
 title={Efficient Algorithms for Ranking with {SVM}s},
 journal={Information Retrieval},
 volume={13},
 number={3},
 pages={201--215},
 year={2010},
 publisher={Springer}
}

@inproceedings{OC11a,
 author={Chapelle, Olivier and Chang, Yi},
 title={Yahoo! Learning to Rank Challenge Overview},
 booktitle={JMLR Workshop and Conference Proceedings: Workshop on Yahoo! Learning to Rank Challenge},
 volume={14},
 pages={1--24},
 year={2011}
}

@conference{OC11b,
	Author = {Olivier Chapelle and Dumitru Erhan},
	Title = {Improved Preconditioner for {H}essian Free Optimization},
	Booktitle = {NIPS Workshop on Deep Learning and Unsupervised Feature Learning},
	Year = {2011}
}


@Article{OC13a,
  author = 	 {Olivier Chapelle and Eren Manavoglu and Romer Rosales},
  title = 	 {Simple and scalable response prediction for display advertising},
 journal = {ACM Transactions on Intelligent Systems and Technology},
    volume={5},
    number={4},
    pages={61:1--61:34},
    year={2015}
}

@Article{OC13a-short,
  author = 	 {Olivier Chapelle and Eren Manavoglu and Romer Rosales},
  title = 	 {Simple and scalable response prediction for display advertising},
  journal = {ACM TIST},
    volume={5},
    number={4},
    pages={61:1--61:34},
    year={2015}
}


@inproceedings{OC14a,
 author = {Chapelle, Olivier},
 title = {Modeling Delayed Feedback in Display Advertising},
 booktitle = {Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)},
 year = {2014},
 pages = {1097--1105}
} 


@Article{FC15a,
  author       = {Francisco Charte and David Charte}, 
  title        = {Working with Multilabel Datasets in {R}: The mldr Package}, 
  journal      = {The R Journal},
  year         = 2015,
  volume       = 7,
  number       = 2,
  pages        = {149--162}
}

@article{BC11a,
  author    = {Biswapesh Chattopadhyay and
               Liang Lin and
               Weiran Liu and
               Sagar Mittal and
               Prathyusha Aragonda and
               Vera Lychagina and
               Younghee Kwon and
               Michael Wong},
  title     = {Tenzing A SQL Implementation On The MapReduce Framework},
  journal   = {Proceedings of the VLDB Endowment},
  volume    = {4},
  number    = {12},
  year      = {2011},
  pages     = {1318-1327}
}

@article{NVC05a,
 author = {Chawla, Nitesh V. and Karakoulas, Grigoris},
 title = {Learning from Labeled and Unlabeled Data: An
Empirical Study Across Techniques and Domains},
 journal = {Journal of Artificial Intelligence Research},
 volume = {23},
 year = {2005},
 pages = {331--366}
}

@Article{BJC02a,
  author = 	 {Bo-Juen Chen and Ming-Wei Chang and
 Chih-Jen Lin},
  title = 	 {Load Forecasting Using Support Vector Machines: A Study on {EUNITE} Competition 2001},
  journal = 	 {IEEE Transactions on Power Systems},
  year={2004},
  volume={19},
  number={4},
month       = {November},
pages       = {1821--1830}
}

@article{CC20a,
title={Efficient Neural Matrix Factorization without Sampling for Recommendation},
author={Chen, Chong and Zhang, Min and Zhang, Yongfeng and Liu, Yiqun and Ma, Shaoping},
journal={ACM Transactions on Information Systems},
volume={38},
number={2},
pages={1--28},
year={2020}
}

@article{CC20a-short,
title={Efficient Neural Matrix Factorization without Sampling for Recommendation},
author={Chen, Chong and Zhang, Min and Zhang, Yongfeng and Liu, Yiqun and Ma, Shaoping},
journal={ACM TIST},
volume={38},
pages={1--28},
year={2020}
}

@inproceedings{CC20b,
title={Efficient Non-Sampling Factorization Machines for Optimal Context-Aware Recommendation},
author={Chen, Chong and Zhang, Min and Ma, Weizhi and Liu, Yiqun and Ma, Shaoping},
booktitle={Proceedings of The Web Conference},
pages={2400--2410},
year={2020}
}

@inproceedings{CC20b-short,
title={Efficient Non-Sampling Factorization Machines for Optimal Context-Aware Recommendation},
author={Chen, Chong and Zhang, Min and Ma, Weizhi and Liu, Yiqun and Ma, Shaoping},
booktitle={The Web Conference},
year={2020}
}

@inproceedings{HC18a,
	title={{HARP}: Hierarchical Representation Learning for Networks},
	author={Chen, Haochen and Perozzi, Bryan and Hu, Yifan and Skiena, Steven},
	booktitle={Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence (AAAI)},
	year={2018}
}

@inproceedings{HC19a,
author = {Chen, Haochen and Sultan, Syed Fahad and Tian, Yingtao and Chen, Muhao and Skiena, Steven},
title = {Fast and Accurate Network Embeddings via Very Sparse Random Projection},
year = {2019},
booktitle = {Proceedings of the 28th ACM International Conference on Information and Knowledge Management (CIKM)},
pages = {399--408}
}

@article{JC09a,
  title={Lanczos vectors versus singular vectors for effective dimension reduction},
  author={Chen, Jie and Yousef Saad},
  journal={IEEE Transactions on Knowledge and Data Engineering},
  volume={21},
  number={8},
  pages={1091--1103},
  year={2009},
  publisher={IEEE}
}

@inproceedings{JC19a,
title={Improving one-class collaborative filtering via ranking-based implicit regularizer},
author={Chen, Jin and Lian, Defu and Zheng, Kai},
booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
volume={33},
pages={37--44},
year={2019}
}

@INPROCEEDINGS{MC11a,
        author = {Mengen Chen and Xiaoming Jin and Dou Shen},
        title = {Short Text Classification Improved by Learning Multi-Granularity Topics},
        booktitle = {Proceedings of the 22nd International Joint Conference on Artificial Intelligence},
        pages = {1776--1781},
        year = {2011},
        editor = {Toby Walsh}
}

 
@INPROCEEDINGS{MC11a-short,
author = {Mengen Chen and Xiaoming Jin and Dou Shen},
title = {Short Text Classification Improved by Learning Multi-Granularity Topics},
booktitle = "IJCAI",
PAGES = {1776-1781},
YEAR = {2011}
}

@inproceedings{MC19a,
  title={Top-k off-policy correction for a {REINFORCE} recommender system},
  author={Chen, Minmin and Beutel, Alex and Covington, Paul and Jain, Sagar and Belletti, Francois and Chi, Ed H},
  booktitle={Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining},
  pages={456--464},
  year={2019}
}

@inproceedings{MC19a-short,
  title={Top-k off-policy correction for a {REINFORCE} recommender system},
  author={Chen, Minmin and Beutel, Alex and Covington, Paul and Jain, Sagar and Belletti, Francois and Chi, Ed H},
  booktitle={WSDM},
  year={2019}
}

@inproceedings{MC21a,
  title={User Response Models to Improve a {REINFORCE} Recommender System},
  author={Chen, Minmin and Chang, Bo and Xu, Can and Chi, Ed H.},
  booktitle={Proceedings of the 14th ACM International Conference on Web Search and Data Mining (WSDM)},
  pages={121--129},
  year={2021}
}

@Article{PHC03a,
  author = 	 {Pai-Hsuen Chen and Chih-Jen Lin and Bernhard Sch\"olkopf},
  title = 	 {A Tutorial on $\nu$-Support Vector Machines},
  year = 	 {2005},
  journal={Applied Stochastic Models in Business and Industry},
  url =	 {http://www.csie.ntu.edu.tw/~cjlin/papers/nusvmtoturial.pdf},
  volume={21},
  issue={2},
  pages={111--136}
}

@Article{PHC05a,
   author =       {Pai-Hsuen Chen and Rong-En Fan and  Chih-Jen Lin},
   title =        {A Study on {SMO}-type Decomposition Methods for Support
Vector Machines},
   journal =      {IEEE Transactions on Neural Networks},
   year = {2006},
   volume = {17},
    pages = {893--908},
    month = {July},
   url =  {http://www.csie.ntu.edu.tw/~cjlin/papers/generalSMO.pdf}
}

@InProceedings{PHC05b,
  author = 	 {Pai-Hsuen Chen and Rong-En Fan and  Chih-Jen Lin},
  title = 	 {Training Support Vector Machines via  SMO-type Decomposition Methods},
  booktitle = 	 {
Proceedings of the 16th International Conference
on Algorithmic Learning Theory (ALT 2005)},
  OPTcrossref =  {},
  OPTkey = 	 {},
  pages =	 {45--62},
  year =	 {2005},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTaddress = 	 {},
  OPTmonth = 	 {},
  OPTorganization = {},
  OPTpublisher = {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}


@misc{PHC18a,
title={A comparison of second-order methods for deep convolutional neural networks},
author={Patrick H. Chen and Cho-Jui Hsieh},
year={2018},
url={https://openreview.net/forum?id=HJYoqzbC-}
}

@mastersthesis{PJC09a,
        author      = {Peng-Jen Chen},
        school      = {Department of Computer Science and Information Engineering, National Taiwan University},
        title       = {{N}ewton Methods for Conditional Random Fields},
        year        = {2009}
}

@InProceedings{PLC11a,
  author =	 {Po-Lung Chen and Chen-Tse Tsai and Yao-Nan Chen and
                  Ku-Chun Chou and Chun-Liang Li and Cheng-Hao Tsai
                  and Kuan-Wei Wu and Yu-Cheng Chou and Chung-Yi Li
                  and Wei-Shih Lin and Shu-Hao Yu and Rong-Bing Chiu
                  and Chieh-Yen Lin and Chien-Chih Wang and Po-Wei
                  Wang and Wei-Lun Su and Chen-Hung Wu and Tsung-Ting
                  Kuo and Todd G. McKenzie and Ya-Hsuan Chang and
                  Chun-Sung Ferng and Chia-Mau Ni and Hsuan-Tien Lin
                  and Chih-Jen Lin and Shou-De Lin },
  title =	 {A Linear Ensemble of Individual and Blended Models
                  for Music Rating Prediction},
  booktitle = {ACM SIGKDD KDD-Cup WorkShop},
  year =	{2011}
}

@InProceedings{PLC11a-short,
  author =	 {Po-Lung Chen and Chen-Tse Tsai and Yao-Nan Chen and Ku-Chun Chou and Chun-Liang Li and
                  others},
  title =	 {A Linear Ensemble of Individual and Blended Models
                  for Music Rating Prediction},
  booktitle = {ACM SIGKDD KDD-Cup WorkShop},
  year =	{2011}
}

@InProceedings{SWC19a,
  author = 	 {Sheng-Wei Chen and Chun-Nan Chou and Edward Y. Chang},
  title = 	 {An Approximate Second-Order Method for Training Fully-Connected Neural Networks},
  OPTcrossref =  {},
  OPTkey = 	 {},
  booktitle = {Proceedings of the Thirty-Third AAAI Conference on
Artificial Intelligence},
  year =	 {2019},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTpages = 	 {},
  OPTmonth = 	 {},
  OPTaddress = 	 {},
  OPTorganization = {},
  OPTpublisher = {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@InProceedings{SWC24a,
  author = 	 {Sheng-Wei Chen and Chih-Jen Lin},
  title = 	 {One-class matrix factorization: point-wise regression-based or pair-wise ranking-based?},
  OPTcrossref =  {},
  OPTkey = 	 {},
  booktitle = {Proceedings of the 18th ACM Recommender Systems Conference},
  year =	 {2024},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTpages = 	 {},
  OPTmonth = 	 {},
  OPTaddress = 	 {},
  OPTorganization = {},
  OPTpublisher = {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@inproceedings{SWC24b,
    title = "Random Label Forests: An Ensemble Method with Label Subsampling For Extreme Multi-Label Problems",
    author = "Chen, Sheng-Wei  and
      Lin, Chih-Jen",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP",
    year = "2024",
    pages = "14107--14119",
    url = {https://www.csie.ntu.edu.tw/~cjlin/papers/random_label_forests/main.pdf}
}


@article{SC17b,
  title={Fast, warped graph embedding: Unifying framework and one-click algorithm},
  author={Chen, Siheng and Niu, Sufeng and Akoglu, Leman and Kova{\v{c}}evi{\'c}, Jelena and Faloutsos, Christos},
  journal={arXiv preprint arXiv:1702.05764},
  year={2017}
}


@InProceedings{SAC22a,
  author = 	 {Si-An Chen and Jie-Jyun Liu and Tsung-Han Yang and Hsuan-Tien Lin and Chih-Jen Lin},
  title = 	 {Even the Simplest Baseline Needs Careful Re-investigation: A Case Study on {XML-CNN}},
  OPTcrossref =  {},
  OPTkey = 	 {},
  booktitle =	 {Proceedings of the Annual Conference of the North {A}merican Chapter of the Association for Computational Linguistics (NAACL)},
  year =	 {2022},
  url = {https://www.csie.ntu.edu.tw/~cjlin/papers/xmlcnn/xml_cnn_study.pdf},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  pages =	 {1987--2000},
  OPTmonth = 	 {},
  OPTaddress = 	 {},
  OPTorganization = {},
  OPTpublisher = {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@InProceedings{SAC22a-short,
  author = 	 {Si-An Chen and Jie-Jyun Liu and Tsung-Han Yang and Hsuan-Tien Lin and Chih-Jen Lin},
  title = 	 {Even the Simplest Baseline Needs Careful Re-investigation: A Case Study on XML-CNN},
  booktitle =	 {NAACL},
  year =	 {2022}
}

@article{SFC00a,
author = {Stanley F. Chen and Ronald
Rosenfeld},
journal = {IEEE Transactions on Speech and
Audio Processing},
pages = {37--50},
title = {A survey of smoothing techniques for
{ME} models},
volume = {8},
number = {1},
year = {2000},
month = {January}
}

@misc{TC16a,
  title={A Reduced-space Algorithm for Minimizing {L}1-regularized Convex Functions},
  author={Chen, Tianyi and Curtis, Frank E. and Robinson, Daniel P.},
  note={arXiv preprint arXiv:1602.07018},
  year={2016}
}

@misc{YC20a,
  title={Predicting {ICD}-9 Codes from Medical Notes--Does the Magic of {BERT} Applies Here?},
  author={Chen, Yiyun},
  year={2020},
  url={https://web.stanford.edu/class/cs224n/reports/custom/report25.pdf}
}


@inproceedings{YC15a,
    title = "Event Extraction via Dynamic Multi-Pooling Convolutional Neural Networks",
    author = "Chen, Yubo  and
      Xu, Liheng  and
      Liu, Kang  and
      Zeng, Daojian  and
      Zhao, Jun",
    booktitle = "Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics",
    year = "2015"
}

@inproceedings{WC14a,
	title={Large-scale {L}-{BFGS} using {M}ap{R}educe},
	author={Chen, Weizhu and Wang, Zhenghao and Zhou, Jingren},
	booktitle={Advances in Neural Information Processing Systems},
	pages={1332--1340},
	year={2014}
}

@inproceedings{WC14a-short,
	title={Large-scale {L}-{BFGS} using {M}ap{R}educe},
	author={Chen, Weizhu and Wang, Zhenghao and Zhou, Jingren},
	booktitle={NIPS},
	year={2014}
}

@Article{WYC11a,
  author = 	 {Wen-Yen Chen and Yangqiu Song and Hongjie Bai and Chih-Jen Lin and Edward Y. Chang},
  title = 	 {Parallel Spectral Clustering in Distributed Systems},
  journal = 	 {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = 	 {2011},
  OPTkey = 	 {},
  volume =	 {33},
  number =	 {3},
  pages =	 {568--586},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}


@inproceedings{YC11a,
 author = {Chen, Ye and Berkhin, Pavel and Anderson, Bo and Devanur, Nikhil R.},
 title = {Real-time Bidding Algorithms for Performance-based Display Ad Allocation},
 booktitle = {Proceedings of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)},
 year = {2011},
 pages = {1307--1315}
} 


@incollection{YW04a,
  author =	{Yi-Wei Chen and Chih-Jen Lin},
  title =	{Combining {SVM}s with various feature selection strategies},
booktitle = {Feature extraction, foundations and applications},
editor = {Isabelle Guyon and Steve Gunn and Masoud Nikravesh and Lofti Zadeh},
publisher = {Springer},
year = "2006"
}

@MastersThesis{YW05a,
  author = 	 {Yi-Wei Chen},
  title = 	 {Combining {SVM}s with various feature selection strategies},
  school = 	 {Department of Computer Science and Information Engineering, National Taiwan University},
  year = 	 {2005}
}

@article{DWC19a,
  title={{BHONEM}: Binary high-order network embedding methods for networked-guarantee loans},
  author={Cheng, Da-Wei and Tu, Yi and Ma, Zhen-Wei and Niu, Zhi-Bin and Zhang, Li-Qing},
  journal={Journal of Computer Science and Technology},
  volume={34},
  pages={657--669},
  year={2019}
}

@inproceedings{HC12a,
 author = {Cheng, Haibin and Zwol, Roelof van and Azimi, Javad and Manavoglu, Eren and Zhang, Ruofei and Zhou, Yang and Navalpakkam, Vidhya},
 title = {Multimedia features for click prediction of new {AD}s in display advertising},
 booktitle = {Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining},
 year = {2012},
 pages = {777--785}
} 

@inproceedings{HTC16a,
title={Wide \& deep learning for recommender systems},
author={Cheng, Heng-Tze and Koc, Levent and Harmsen, Jeremiah and Shaked, Tal and Chandra, Tushar and Aradhye, Hrishi and Anderson, Glen and Corrado, Greg and Chai, Wei and Ispir, Mustafa and others},
booktitle={Proceedings of the 1st Workshop on Deep Learning for Recommender Systems},
pages={7--10},
year={2016}
}

@inproceedings{HTC16a-short,
title={Wide \& deep learning for recommender systems},
author={Cheng, Heng-Tze and Koc, Levent and Harmsen, Jeremiah and Shaked, Tal and Chandra, Tushar and Aradhye, Hrishi and Anderson, Glen and Corrado, Greg and Chai, Wei and Ispir, Mustafa and others},
booktitle={Workshop on Deep Learning for Recommender Systems},
year={2016}
}


@techreport{SHC96a,
author      = "Sheung Hun Cheng and Nicholas J. Higham",
title       = "A modified {Cholesky} algorithm based on a symmetric indefinite
               factorization",
institution = "University of Manchester",
address     = "Manchester M13 9PL, England",
type        = "Numerical Analysis Report",
number      = "No. 289",
pages       = "18",
month       = "April",
year        = "1996"
}

@article{VC04a,
    title={Practical selection of SVM parameters and noise estimation for SVM regression},
    author={Vladimir Cherkassky and Yunqian Ma},
    journal={Neural networks},
    year={2004},
    volume={17},
    pages={113-126}
}

@InProceedings{HGC01a,
  author = 	 {Hong-Gunn Chew and Robert E. Bogner and Cheng-Chew Lim},
  title = 	 {Dual $\nu$-Support Vector Machine with error rate and training size biasing},
  booktitle = 	 {Proceedings of ICASSP},
  pages={1269--72},
  year =	 {2001}
}


@InProceedings{HGC03a,
  author = 	 {H. G. Chew and C. C. Lim and R. E. Bogner},
  title = 	 {An implementation of training dual-nu support vector machines},
  booktitle = 	 {Optimization and Control with Applications},
  year =	 {2003},
  editor =	 {Qi and Teo and Yang},
  publisher =	 {Kluwer}
}


@InProceedings{WLC16a,
  author = 	 {Wei-Lin Chiang and Mu-Chu Lee and Chih-Jen Lin},
  title = 	 {Parallel dual coordinate descent method for large-scale linear classification in multi-core environments},
  year = 	 {2016},
  booktitle =	 {Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)},
  url = {http://www.csie.ntu.edu.tw/~cjlin/papers/multicore_cddual.pdf},
  OPTkey = 	 {},
  OPTtype = 	 {},
  OPTnumber = 	 {},
  OPTaddress = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@InProceedings{WLC16a-short,
  author = 	 {Wei-Lin Chiang and Mu-Chu Lee and Chih-Jen Lin},
  title = 	 {Parallel dual coordinate descent method for large-scale linear classification in multi-core environments},
  year = 	 {2016},
  booktitle =	 {KDD}
}

@InProceedings{WLC17a,
  author = {Wei-Lin Chiang and Yu-Sheng Li and Ching-Pei Lee and Chih-Jen Lin},
  title = 	 {Limited-memory Common-directions Method for Distributed L1-regularized Linear Classification},
  booktitle =	 {Proceedings of SIAM International Conference on Data Mining (SDM)},
  year =	 {2018},
  url={http://www.csie.ntu.edu.tw/~cjlin/papers/l-commdir-l1/OWL-commdir.pdf}
}

@MastersThesis{KC98a,
  author = 	 {K. K. Chin},
  title = 	 {Support Vector Machines applied to Speech Pattern Classification},
  school = 	 {University of Cambridge},
  year = 	 {1998},
}


@inproceedings{WSC13a,
author = {Chin, Wei-Sheng and Juan, Yu-Chin and Zhuang, Yong and Wu, Felix and Tung, Hsiao-Yu and Yu, Tong and Wang, Jui-Pin and Chang, Cheng-Xia and Yang, Chun-Pai and Chang, Wei-Cheng and Huang, Kuan-Hao and Kuo, Tzu-Ming and Lin, Shan-Wei and Lin, Young-San and Lu, Yu-Chen and Su, Yu-Chuan and Wei, Cheng-Kuang and Yin, Tu-Chun and Li, Chun-Liang and Lin, Ting-Wei and Tsai, Cheng-Hao and Lin, Shou-De and Lin, Hsuan-Tien and Lin, Chih-Jen},
title = {Effective String Processing and Matching for Author Disambiguation},
booktitle = {Proceedings of the KDD Cup 2013 Workshop},
year = {2013},
pages = {7:1--7:9},
publisher = {ACM},
}

@article{WSC14a,
  author  = {Wei-Sheng Chin and Yong Zhuang and Yu-Chin Juan and Felix Wu and Hsiao-Yu Tung and Tong Yu and Jui-Pin Wang and Cheng-Xia Chang and Chun-Pai Yang and Wei-Cheng Chang and Kuan-Hao Huang and Tzu-Ming Kuo and Shan-Wei Lin and Young-San Lin and Yu-Chen Lu and Yu-Chuan Su and Cheng-Kuang Wei and Tu-Chun Yin and Chun-Liang Li and Ting-Wei Lin and Cheng-Hao Tsai and Shou-De Lin and Hsuan-Tien Lin and Chih-Jen Lin},
  title   = {Effective String Processing and Matching for Author Disambiguation},
  journal = {Journal of Machine Learning Research},
  year    = {2014},
  volume  = {15},
  pages   = {3037--3064}
}



@Article{WSC15a,
  author = 	 {Wei-Sheng Chin and Yong Zhuang and Yu-Chin Juan and Chih-Jen Lin},
  title = 	 {A Fast Parallel Stochastic Gradient Method for Matrix Factorization in Shared Memory Systems},
 journal = {ACM Transactions on Intelligent Systems and Technology},
  OPTpages = 	 {},
  year =	 {2015},
  OPTeditor = 	 {},
  volume =	 {6},
  url = {http://www.csie.ntu.edu.tw/~cjlin/papers/libmf/libmf_journal.pdf},
  OPTnumber = 	 {},
  pages =	 {2:1--2:24},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@Article{WSC15a-short,
  author =       {Wei-Sheng Chin and Yong Zhuang and Yu-Chin Juan and
Chih-Jen Lin},
  title =        {A Fast Parallel Stochastic Gradient Method for Matrix
Factorization in Shared Memory Systems},
 journal = {ACM TIST},
  OPTpages =     {},
  year =         {2015},
  OPTeditor =    {},
  volume =       {6},
  OPTnumber =    {},
  pages =        {2:1--2:24},
  OPTmonth =     {},
  OPTnote =      {},
  OPTannote =    {}
}

@InProceedings{WSC15b,
  author = 	 {Wei-Sheng Chin and Yong Zhuang and Yu-Chin Juan and Chih-Jen Lin},
  title = 	 {A Learning-rate Schedule for Stochastic Gradient Methods to Matrix Factorization},
  OPTcrossref =  {},
  OPTkey = 	 {},
  booktitle =	 {Proceedings of the Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD)},
  year =	 {2015},
  url = {http://www.csie.ntu.edu.tw/~cjlin/papers/libmf/mf_adaptive_pakdd.pdf},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTpages = 	 {},
  OPTmonth = 	 {},
  OPTaddress = 	 {},
  OPTorganization = {},
  OPTpublisher = {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@InProceedings{WSC15b-short,
  author = 	 {Wei-Sheng Chin and Yong Zhuang and Yu-Chin Juan and Chih-Jen Lin},
  title = 	 {A Learning-rate Schedule for Stochastic Gradient Methods to Matrix Factorization},
  booktitle =	 {PAKDD},
  year =	 {2015}
}


@article{WSC15c,
	author =      {Wei-Sheng Chin and Bo-Wen Yuan and Meng-Yuan Yang and Yong Zhuang and Yu-Chin Juan and Chih-Jen Lin},
	title =       {{LIBMF}: A Library for Parallel Matrix Factorization in Shared-memory Systems},
  journal   = {Journal of Machine Learning Research},
  year      = {2016},
  volume  = {17},
  number  = {86},
  pages   = {1-5},
  url = {https://www.csie.ntu.edu.tw/~cjlin/papers/libmf/libmf_open_source.pdf}
}

@article{WSC15c-short,
	author =      {Wei-Sheng Chin and Bo-Wen Yuan and Meng-Yuan Yang and Yong Zhuang and Yu-Chin Juan and Chih-Jen Lin},
	title =       {{LIBMF}: A Library for Parallel Matrix Factorization in Shared-memory Systems},
  journal   = {JMLR},
  year      = {2016},
  volume  = {17},
  number  = {86},
  pages   = {1-5}
}

@techreport{WSC16a,
  author = {Chin, Wei-Sheng and Yuan, Bo-Wen and Yang, Meng-Yuan and Lin, Chih-Jen},
  title = {A Note on Diagonal Preconditioner in Large-scale Logistic Regression},
  institution = {Department of Computer Science and Information Engineering, National Taiwan University},
  url={https://www.csie.ntu.edu.tw/~cjlin/papers/logistic/pcgnote.pdf},
  year={2016}
}

@techreport{WSC16a-short,
  author = {Chin, Wei-Sheng and Yuan, Bo-Wen and Yang, Meng-Yuan and Lin, Chih-Jen},
  title = {A Note on Diagonal Preconditioner in Large-scale Logistic Regression},
  institution = {National Taiwan University},
  url={https://www.csie.ntu.edu.tw/~cjlin/papers/logistic/pcgnote.pdf},
  year={2016}
}



@Article{WSC18a,
  author = 	 {Wei-Sheng Chin and Bo-Wen Yuan and Meng-Yuan Yang and Chih-Jen Lin},
  title = 	 {An Efficient Alternating {N}ewton Method for Learning Factorization
Machines},
  journal = 	 {ACM Transactions on Intelligent Systems and Technology},
  year = 	 {2018},
  volume = {9},
  number = {6},
  pages = {72:1--72:31},
  url = {https://www.csie.ntu.edu.tw/~cjlin/papers/fm/scalefm.pdf},
  OPTkey = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTpages = 	 {},
  OPTmonth = 	 {},
  OPTannote = 	 {}
}

@Article{WSC18a-short,
  author =       {Wei-Sheng Chin and Bo-Wen Yuan and Meng-Yuan Yang and Chih-Jen Lin},
  title =        {An Efficient Alternating {N}ewton Method for Learning Factorization
Machines},
  journal =      {ACM TIST},
  year =         {2018},
  volume = {9},
  pages = {72:1--72:31}
}

@article{SC94a,
  title={The application of automatic differentiation to problems in engineering analysis},
  author={Chinchalkar, Shirish},
  journal={Computer Methods in Applied Mechanics and Engineering},
  volume={118},
  number={1-2},
  pages={197--207},
  year={1994}
}

@InProceedings{CCC18a,
	author = {Chi-Cheng Chiu and Pin-Yen Lin and Chih-Jen Lin},
	title = {Two-variable Block Dual Coordinate Descent Methods for Large-scale Linear Support Vector Machines},
        booktitle = {Proceedings of SIAM International Conference on Data Mining (SDM)},
	year = {2020},
        url = {https://www.csie.ntu.edu.tw/~cjlin/papers/2var_cd/twocddual.pdf}
}
	
@InProceedings{CCC18a-short,
	author = {Chi-Cheng Chiu and Pin-Yen Lin and Chih-Jen Lin},
	title = {Two-variable Block Dual Coordinate Descent Methods for Large-scale Linear Support Vector Machines},
        booktitle = {SDM},
	year = {2020}
}

@misc{FC15c,
   title={Keras},
   author={Chollet, Fran\c{c}ois and others},
   year={2015},
   howpublished={\url{https://keras.io}},
}

@InProceedings{HYC20a,
	author = {Hung-Yi Chou and Pin-Yen Lin and Chih-Jen Lin},
	title = {Dual Coordinate-Descent Methods for Linear One-Class {SVM} and {SVDD}},
        booktitle = {Proceedings of SIAM International Conference on Data Mining (SDM)},
	year = {2020},
	url= {http://www.csie.ntu.edu.tw/~cjlin/papers/linear_oneclass_SVM/siam.pdf}
}

@InProceedings{HYC20a-short,
	author = {Hung-Yi Chou and Pin-Yen Lin and Chih-Jen Lin},
	title = {Dual Coordinate-Descent Methods for Linear One-Class {SVM} and {SVDD}},
        booktitle = {SDM},
	year = {2020}
}



@InProceedings{BYC15a,
  author = 	 {Bo-Yu Chu and Chia-Hua Ho and Cheng-Hao Tsai and Chieh-Yen Lin and Chih-Jen Lin},
  title = 	 {Warm Start for Parameter Selection of Linear Classifiers},
  OPTcrossref =  {},
  OPTkey = 	 {},
  booktitle =	 {Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)},
  year =	 {2015},
  url = {http://www.csie.ntu.edu.tw/~cjlin/libsvmtools/warm-start/warm-start.pdf},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTpages = 	 {},
  OPTmonth = 	 {},
  OPTaddress = 	 {},
  OPTorganization = {},
  OPTpublisher = {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@InProceedings{BYC15a-short,
  author = 	 {Bo-Yu Chu and Chia-Hua Ho and Cheng-Hao Tsai and Chieh-Yen Lin and Chih-Jen Lin},
  title = 	 {Warm Start for Parameter Selection of Linear Classifiers},
  booktitle =	 {KDD},
  year =	 {2015}
}

@incollection{CTC07a,
 title = {Map-Reduce for Machine Learning on Multicore},
 author = {Cheng-Tao Chu and Sang Kyun Kim and Yi-An Lin and YuanYuan Yu and Gary Bradski and Andrew Y. Ng and Kunle Olukotun},
 booktitle = {Advances in Neural Information Processing Systems 19},
 editor = {B. Sch\"{o}lkopf and J. Platt and T. Hoffman},
 publisher = {MIT Press},
 address = {Cambridge, MA},
 pages = {281--288},
 year = {2007}
}


@inproceedings{DC11a,
 author = {Chu, David and Lane, Nicholas D. and Lai, Ted Tsung-Te and Pang, Cong and Meng, Xiangying and Guo, Qing and Li, Fan and Zhao, Feng},
 title = {Balancing energy, latency and accuracy for mobile sensor data classification},
 booktitle = {Proceedings of the 9th ACM Conference on Embedded Networked Sensor Systems (SenSys)},
 year = {2011},
 pages = {54--67}
}

@Article{MC04a,
  author = 	 {M. Chu and F. Diele and R. Plemmons and S. Ragni},
  title = 	 {Optimality, Computation and Interpretation of nonnegative matrix factorizations},
  year = 	 {2005},
  OPTkey = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTpages = 	 {},
  OPTmonth = 	 {},
  OPTannote = 	 {},
  url = {http://www.wfu.edu/~plemmons/papers/chu_ple.pdf}
}


@Article{MC04a-short,
  author = 	 {M. Chu and F. Diele and R. Plemmons and S. Ragni},
  title = 	 {Theory, numerical methods and applications of the nonnegative matrix factorization},
  year = 	 {2004},
}

@Article{WC03a,
  author = 	 {Wei Chu and S. Sathiya Keerthi and Chong Jin Ong},
  title = 	 {Bayesian Support Vector Regression Using a Unified Loss
Function},
  journal = 	 {IEEE Transactions on Neural Networks},
  year = 	 {2004},
  volume={15},
pages={29--44}
}

@PhdThesis{WC03b,
  author = {Wei Chu},
  title = {Bayesian approach to support vector machines},
  school = {National University of Singapore},
  year = {2003}
}

@Article{WC03c,
  author = {W. Chu and S.S. Keerthi and C.J. Ong},
  title = {Bayesian trigonometric support vector classifier},
  journal = {Neural Computation},
  pages = {2227--2254},
  volume = {15},
  number = {9},
  year = {2003},
}

@article{BGC13a,
	title={{REEF}: Retainable evaluator execution framework},
	author={Chun, Byung-Gon and Condie, Tyson and Curino, Carlo and Douglas, Chris and Matusevych, Sergiy and Myers, Brandon and Narayanamurthy, Shravan and Ramakrishnan, Raghu and Rao, Sriram and Rosen, Josh and 
	Russell Sears and
	Markus Weimer},
	journal={Proceedings of the {VLDB} Endowment},
	volume={6},
	number={12},
	pages={1370--1373},
	year={2013},
	publisher={VLDB Endowment}
}

@Article{KC02b,
author = 	 {Kai-Min Chung and Wei-Chun Kao and 
Chia-Liang Sun and  Li-Lun Wang  and  Chih-Jen Lin},
  title = 	 {Radius Margin Bounds for Support Vector Machines with the {RBF} Kernel},
 journal     ={Neural Computation},
volume      = {15},
  pages={2643--2681},
  year =	 {2003}
}

@Article{KC02b-short,
author = 	 {K.-M. Chung and W.-C. Kao and 
C.-L. Sun and  L.-L. Wang  and  C.-J. Lin},
  title = 	 {Radius Margin Bounds for Support Vector Machines with the {RBF} Kernel},
 journal     ={Neural Comput.},
volume      = {15},
  pages={2643--2681},
  year =	 {2003}
}

@InProceedings{KC02c,
author = 	 {Kai-Min Chung and Wei-Chun Kao and 
Tony Sun and  Li-Lun Wang  and  Chih-Jen Lin},
  title = 	 {Radius Margin Bounds for Support Vector Machines with the {RBF} Kernel},
  year = 	 {2002},
  pages = {893--897},
  booktitle = 	 {Proceedings of ICONIP 2002}
}


@InProceedings{KC03a,
  author = 	 {Kai-Min Chung and 
 Wei-Chun Kao and  Tony Sun and  Chih-Jen Lin},
  title = 	 {Decomposition Methods for Linear Support Vector Machines},
  year = 	 {2003},
  pages={868--871},
  booktitle = 	 {Proceedings of ICASSP 2003}
}





@article{EChow97a,
author={E. Chow and Y. Saad}, 
title={Experimental study of {ILU} preconditioners for indefinite
matrices},
journal={J. Comput. Appl. Math.},
volume={87},pages={387--414},year={1997}} 


@article{EC98a,
title={Approximate inverse preconditioners 
via sparse-sparse iterations}, 
author={E. Chow and Y. Saad},
journal={SIAM J. Sci. Comput.},
volume={19},year={1998},
pages={995--1023}}

@Article{AC09a,
  author = 	 {Andrzej Cichocki and Anh-Huy Phan},
  title = 	 {Fast local algorithms for
large scale nonnegative matrix and tensor
factorizations},
  journal = 	 {IEICE Transaction on Fundamentals},
  year = 	 {2009},
  OPTkey = 	 {},
  volume =	 {E92-A},
  OPTnumber = 	 {},
  pages =	 {708--721},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@article{DCC10a,
  title={Deep, big, simple neural nets for handwritten digit recognition},
  author={Ciresan, Dan Claudiu and Meier, Ueli and Gambardella, Luca Maria
and Schmidhuber, J{\"u}rgen},
  journal={Neural Computation},
  volume={22},
  pages={3207--3220},
  year={2010}
}

@InProceedings{AC01a,
  author = 	 {Clare, A. and King, R.D. },
  title = 	 {Knowledge Discovery in Multi-Label Phenotype Data},
  booktitle = 	 {Proceedings of ECML/PKDD},
  OPTcrossref =  {},
  OPTkey = 	 {},
  OPTpages = 	 {},
  year =	 {2001},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTaddress = 	 {},
  OPTmonth = 	 {},
  OPTorganization = {},
  OPTpublisher = {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@InProceedings{AC01a-short,
  author = 	 {Clare, A. and King, R.D. },
  title = 	 {Knowledge Discovery in Multi-Label Phenotype Data},
  booktitle = 	 {ECML/PKDD},
  OPTcrossref =  {},
  OPTkey = 	 {},
  OPTpages = 	 {},
  year =	 {2001},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTaddress = 	 {},
  OPTmonth = 	 {},
  OPTorganization = {},
  OPTpublisher = {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@Book{FC83,
  author =	 {F. H. Clarke},
  title = 	 {Optimization and Nonsmooth Analysis},
  publisher = {Wiley},
  year = 	 {1983},
  address =	 {New York}
}

@unpublished{MC12a,
    TITLE = {Standard Particle Swarm Optimisation},
    AUTHOR = {Clerc, Maurice},
    URL = {https://hal.archives-ouvertes.fr/hal-00764996},
    YEAR = {2012}
}

@article{CC84a,
  title={{Optimizing convenient online access to bibliographic databases}},
  author={Cleverdon, C.},
  journal={Information Services and Use},
  volume={4},
  number={1--2},
  pages={37--47},
  year={1984},
  publisher={IOS Press Amsterdam, The Netherlands, The Netherlands}
}

@ARTICLE{LC14a,
  author={Clifton, Lei and Clifton, David A. and Zhang, Yang and Watkinson, Peter and Tarassenko, Lionel and Yin, Hujun},
  journal={IEEE Transactions on Reliability}, 
  title={Probabilistic Novelty Detection With Support Vector Machines}, 
  year={2014},
  volume={63},
  number={2},
  pages={455--467}
}

@ARTICLE{LC14a-short,
  author={Clifton, Lei and Clifton, David A. and Zhang, Yang and Watkinson, Peter and Tarassenko, Lionel and Yin, Hujun},
  journal={IEEE Trans. Reliab.}, 
  title={Probabilistic Novelty Detection With Support Vector Machines}, 
  year={2014},
  volume={63},
  pages={455--467}
}

@inbook{MBC15a,
author = {Michael B. Cohen and Cameron Musco and Christopher Musco},
title = {Input Sparsity Time Low-rank Approximation via Ridge Leverage Score Sampling},
booktitle = {Proceedings of the Twenty-Eighth Annual ACM-SIAM Symposium on Discrete Algorithms},
pages = {1758-1777}
}
                                  
@article{TFC93a,
author      = {T. F. Coleman and L. A. Hulbert},
journal     = {SIAM J. Optim.},
pages       = {298--321},
title       = {A globally and superlinearly convergent algorithm 
               for convex quadratic programming programs with 
               simple bounds},
volume      = {3},
year        = {1993}
}

@article{TFC93c,
author      = {T. F. Coleman and Y. Li},
title       = {An interior trust region approach for nonlinear minimization
               subject to bounds},
journal     = {SIAM J. Optim.},
pages       = {418--445},
volume      = {6},
year        = {1996}
}

@TechReport{TFC97a,
author      = {T. F. Coleman and Y. Li},
title       = {Combining trust region and affine scaling for
               linearly constrained nonconvex minimization},
institution = {Cornell University},
number      = {TR97-1641},
address     = {Ithaca, New York},
type        = {Technical Report},
year        = {1997},
}

@TechReport{TFC97b,
author      = {T. F. Coleman and Y. Li},
title       = {A trust region and affine scaling interior point
               method for nonconvex minimization with linear
               inequality constraints},
institution = {Cornell University},
number      = {TR97-1642},
address     = {Ithaca, New York},
type        = {Technical Report},
year        = {1997},
}

@article{MC02a,
author      = {Michael Collins and Robert E. Schapire and Yoram Singer},
journal     = {Machine Learning},
pages       = {253--285},
title       = {Logistic regression, {A}da{B}oost and {B}regman distances},
volume      = {48},
number      = {1--3},
year        = {2002},
publisher   = {Springer, Dordrecht}
}

@Article{MC07a,
  title={Exponentiated Gradient Algorithms for Conditional Random
Fields and Max-Margin {M}arkov Networks},
  author =       {Michael Collins and Amir Globerson and Terry Koo and
Xavier Carreras and Peter Bartlett},
  journal   = {Journal of Machine Learning Research},
  year      = {2008},
  pages     = {1775--1822},
  volume    = {9}
}

@Article{MC07a-short,
  title={Exponentiated Gradient Algorithms for Conditional Random
Fields and Max-Margin {M}arkov Networks},
  author =       {Michael Collins and Amir Globerson and Terry Koo and
Xavier Carreras and Peter Bartlett},
  journal = 	 {JMLR},
 year = {2008},
  pages     = {1775--1822},
  volume    = {9}
}

@Article{RC01a,
  author =	 {Ronan Collobert and Samy Bengio},
  journal = 	 {Journal of Machine Learning Research},
  title =	 {{SVMT}orch: A Support Vector Machine for Large-Scale
     Regression and Classification Problems},
  year = {2001},
volume   = {1},
pages       = {143--160},
  url = {http://www.idiap.ch/learning/SVMTorch.html}

}

@Article{RC02a,
   author = {Collobert, R. and Bengio, S. and Bengio, Y.},
   title = {A Parallel Mixture of {SVMs} for Very Large Scale Problems},
   journal = {Neural Computation},
   year = {2002},
   volume = 14,
   number = 05,
   pages = {1105--1114},
   ipdmembership="learning",
   ipdpostscript="ftp://ftp.idiap.ch/pub/reports/2001/rr01-12.ps.gz",
   IPDpdf   ="ftp://ftp.idiap.ch/pub/reports/2001/rr01-12.pdf",
   ipdxref = "techreport:collobert-rr-01-12.bib"
}

@techreport{PC76a,
 title = {A generalized conjugate gradient method for the numerical solution of elliptic partial differential equations},
 author = {Concus, Paul and Golub, Gene H and O\'Leary, Dianne P},
 year = {1976},
 publisher={Computer Science Department, Stanford University},
 number      = {STAN-CS-76-533}
}

@techreport{PC76a-short,
 title = {A generalized conjugate gradient method for the numerical solution of elliptic partial differential equations},
 author = {Concus, Paul and Golub, Gene H and O\'Leary, Dianne P},
 year = {1976},
 publisher={Stanford University}
}

@article{ARC88a,
author      = {A. R. Conn and N. I. M. Gould and Ph. L. Toint},
journal     = {Math. Comp.},
pages       = {399--430},
title       = {Testing a class of methods for solving minimization 
problems with simple bounds on the variables},
volume      = {50},
year        = {1988}
}

@article{ARC88,
author      = {A. R. Conn and N. I. M. Gould and Ph. L. Toint},
journal     = {SIAM J. Numer. Anal.},
pages       = {433--460},
title       = {Global convergence of a class of trust region algorithms for optimization problems with simple bounds},
volume      = {25},
year        = {1988},
note        = {Correction in {\em SIAM J. Numer. Anal.}, 26 (1989), 764--767.}
}



@Book{ARC92,
  author = 	 {A. R. Conn and N. I. M. Gould and Ph. L. Toint},
  title = 	 {\sf LANCELOT},
  publisher = 	 {Springer-Verlag},
  year = 	 {1992},
  series =	 {Springer Series in Computational Mathematics}
}

@inproceedings{ARC92a,
author      = {A. R. Conn and N. I. M. Gould and Ph. L. Toint},
booktitle   = {Proceedings of the Second International Conference on
Industrial and Applied Mathematics},
editor      = {R. E. O'Malley},
pages       = {51--70},
publisher   = {SIAM},
title       = {Large-scale nonlinear constrained optimization},
year        = {1992}
}

@article{ARC93,
author      = {A. R. Conn and N. I. M. Gould and A. Sartenaer 
               and Ph. L. Toint},
title       = {Global convergence of a class of trust region algorithms
               for optimization using inexact projections on convex constraints},
journal     = {SIAM J. Optim.},
volume      = {3},
pages       = {164--221},
year        = {1993}
}

@article{ARC96a,
author      = {A. R. Conn and N. I. M. Gould and Ph. L. Toint},
title       = {Numerical experiments with the {{\sf LANCELOT}} package
               ({R}elease {A}) for large-scale nonlinear optimization},
journal     = {Math. Programming},
volume      = {73},
pages       = {73--110},
year        = {1996}
}


@inproceedings{SC08a,
author = {Consolvo, Sunny and McDonald, David W. and Toscos, Tammy and Chen, Mike Y. and Froehlich, Jon and Harrison, Beverly and Klasnja, Predrag and LaMarca, Anthony and LeGrand, Louis and Libby, Ryan and Smith, Ian and Landay, James A.},
title = {Activity sensing in the wild: a field trial of ubifit garden},
booktitle = {Proceedings of the SIGCHI Conference on Human Factors in Computing Systems},
series = {CHI '08},
year = {2008},
isbn = {978-1-60558-011-1},
location = {Florence, Italy},
pages = {1797--1806},
numpages = {10},
url = {http://doi.acm.org/10.1145/1357054.1357335},
doi = {10.1145/1357054.1357335},
acmid = {1357335},
publisher = {ACM},
address = {New York, NY, USA},
keywords = {activity inference, activity-based applications, ambient display, fitness, mobile phone, persuasive technology, physical activity, sensing},
}

@book{ARC00a,
 author = {Conn, Andrew R. and Gould, Nicholas I. M. and Toint, Philippe L.},
 title = {Trust-region Methods},
 publisher = {Society for Industrial and Applied Mathematics},
 address = {Philadelphia},
 year = {2000},
} 

@book{ARC00a-short,
 author = {Conn, Andrew R. and Gould, Nicholas I. M. and Toint, Philippe L.},
 title = {Trust-region Methods},
 publisher = {SIAM},
 year = {2000}
} 

@book{THC01a,
 author={Cormen, Thomas H. and Leiserson, Charles E. and Rivest, Ronald L. and Stein, Clifford},
 title={Introduction to Algorithms},
 year={2001},
 publisher={MIT press}
}

@article{GC05a,
 title = {An Improved Data Stream Summary: the Count-min Sketch and
Its Applications},
 author = {Cormode, Graham and Muthukrishnan, S.},
 journal = {Journal of Algorithms},
 volume = {55},
 pages = {58--75},
 year = {2005}
}

@Article{CC95a,
  author = 	 {Corina Cortes and Vladimir Vapnik},
  title = 	 {Support-vector network},
  journal = 	 {Machine Learning},
  year = 	 {1995},
  volume =	 {20},
  pages =	 {273--297}
}

@Article{CC95a-short,
  author = 	 {Corina Cortes and Vladimir Vapnik},
  title = 	 {Support-vector network},
  journal = 	 {MLJ},
  year = 	 {1995},
  volume =	 {20},
  pages =	 {273--297}
}

@article{EC11a,
  author = {Cortez, Eli and Rojas Herrera, Mauro and da Silva, Altigran S. and de Moura, Edleno S. and Neubert, Marden},
  title = {Lightweight methods for large-scale product categorization},
  journal = {JASIST},
  volume = {62},
  year = {2011},
  pages = {1839--1848},
}

@inproceedings{CC03a,
  author    = {Corinna Cortes and
               Patrick Haffner and
               Mehryar Mohri},
  title     = {Positive Definite Rational Kernels.},
  booktitle = {Proceedings of the 16th Annual Conference on Learning Theory},
  year      = {2003},
  pages     = {41--56}
}

@inproceedings{MC15a,
 author = {Courbariaux, Matthieu and Bengio, Yoshua and David, Jean-Pierre},
 booktitle = {Advances in Neural Information Processing Systems},
 title = {{B}inary{C}onnect: Training Deep Neural Networks with binary weights during propagations},
 volume = {28},
 year = {2015},
 pages = {3123--3131}
}

@inproceedings{MC15a-short,
 author = {Courbariaux, Matthieu and Bengio, Yoshua and David, Jean-Pierre},
 booktitle = {NIPS},
 title = {{B}inary{C}onnect: Training Deep Neural Networks with binary weights during propagations},
 year = {2015}
}

@Article{TC65a,
  author = 	 {T. Cover},
  title = 	 {Geometrical and statistical properties of systems of
linear inequalities with applications in pattern recognition},
  journal = 	 {IEEE Transactions on Electronic Computers},
  year = 	 {1965},
  volume =	 {EC-14},
  pages =	 {326--334}
}

@article{DRC58a,
  title={The Regression Analysis of Binary Sequences},
  author={Cox, David R.},
  journal={Journal of the Royal Statistical Society: Series B (Methodological)},
  volume={20},
  number={2},
  pages={215--232},
  year={1958}
}

@TechReport{JSC02a,
  author = {Jan Salomon Cramer},
  title = {The Origins of Logistic Regression},
  institution = {Tinbergen Institute},
  year = {2002},
  url = {http://ideas.repec.org/p/dgr/uvatin/20020119.html}
}

@InProceedings{KC00a,
    author = "Koby Crammer and Yoram Singer",
    title = "On the Learnability and Design of Output Codes for Multiclass Problems",
    booktitle = "Computational Learning Theory",
    pages = "35--46",
    year = "2000"
}
%     url = "http://citeseer.nj.nec.com/275630.html"

@InProceedings{KC00a-short,
    author = "Koby Crammer and Yoram Singer",
    title = "On the Learnability and Design of Output Codes for Multiclass Problems",
    booktitle = "COLT",
    year = "2000"
}

@TechReport{KC01a,
    author = "Koby Crammer and Yoram Singer",
    title = "Ultraconservative online algorithms for Multiclass Problems",
  institution =  {School of Computer Science and Engineering,
Hebrew University}, 
  year = 	 {2001},
  OPTaddress = 	 {Jerusalem 91904, Israel}
}

@TechReport{KC01b,
    author = "Koby Crammer and Yoram Singer",
    title = "On the Learnability and Design of Output Codes for Multiclass Problems",
  institution =  {School of Computer Science and Engineering,
Hebrew University}, 
  year = 	 {2001},
  OPTaddress = 	 {Jerusalem 91904, Israel}
}

@Article{KC01c,
    author = "Koby Crammer and Yoram Singer",
    title = "On the algorithmic implementation of multiclass kernel-based vector machines",
   journal={Journal of Machine Learning Research},
   volume={2},
  pages={265--292},
  year = 	 {2001}
}

@Article{KC01c-short,
    author = "Koby Crammer and Yoram Singer",
    title = "On the algorithmic implementation of multiclass kernel-based vector machines",
   journal={JMLR},
   volume={2},
  pages={265--292},
  year = 	 {2001}
}

@article{KC02d,
    author = {Koby Crammer and Yoram Singer},
    title = {On the Learnability and Design of Output Codes for
Multiclass Problems},
    journal = {Machine Learning},
    volumn = {47},
    number = {2--3},
    pages = {201--233},
    year = {2002}
}


@Article{KC03a-short,
 author =   {Koby Crammer and Yoram Singer},
  title =    {Ultraconservative Online Algorithms for Multiclass Problems},
  year =     {2003},
  journal = {JMLR},
  volume      = {3},
  pages={951--991}
}

@inproceedings{PSC05a,
  title={A method for optimal division of data sets for use in neural networks},
  author={Crowther, Patricia S. and Cox, Robert J.},
  booktitle={International Conference on Knowledge-based and Intelligent Information and Engineering Systems},
  pages={1--7},
  year={2005}
}

@inproceedings{PSC05a-short,
  title={A method for optimal division of data sets for use in neural networks},
  author={Crowther, Patricia S. and Cox, Robert J.},
  booktitle={KES},
  year={2005}
}

@InProceedings{DJC99a,
  author = 	 {D. J. Crisp and C. J. C. Burges},
  title = 	 {A geometric interpretation of $\nu$-{SVM} classifiers},
  booktitle = 	 {Advances in Neural Information Processing Systems},
  volume = {12},
  editor={Sara Solla and Todd Leen and Klaus-Robert M{\"u}ller},
  publisher={MIT Press},
  address =	 {Cambridge, MA},
  year =	 {2000}
}

@InProceedings{Cristianini99a,
  author        = {N. Cristianini and C. Campbell and J. Shawe-Taylor},
  title         = {Dynamically Adapting Kernels in Support Vector Machines.},
  booktitle = {Advances in Neural Information Processing Systems},
  editor = {Michael S. Kearns and Sara A. Solla and David A. Cohn},
  address = {Cambridge, MA},
  year          = {1999},
  pages         = {204--210},
  publisher	= {{MIT} Press},
  volume        = {11},
  url           = {/papers/upload_13617_nips98.ps}
}

@Book{NC00a,
  author        = {N.~Cristianini and J.~Shawe-Taylor},
  title         = {An Introduction to Support Vector Machines},
  publisher     = {Cambridge University Press},
  address       = {Cambridge, UK},
  year          = {2000}
}
%  note          = {For further information, click <A
%                  HREF="http://www.support-vector.net">here.</A>}

@Misc{CRITEO15a,
author = {Criteo},
title = {Criteo Releases Industry’s Largest-Ever Dataset for Machine Learning to Academic Community},
year = {2015},
howpublished = {\url{
http://www.criteo.com/news/press-releases/2015/06/criteo-releases-industrys-largest-ever-dataset/}}
}

@InProceedings{DC15a,
  title = 	 {Stochastic Dual Coordinate Ascent with Adaptive Probabilities},
  author = 	 {Dominik Csiba and Zheng Qu and Peter Richt\'{a}rik},
  booktitle = 	 {Proceedings of the 32nd International Conference on Machine Learning},
  pages = 	 {674--683},
  year = 	 {2015}
}

@InProceedings{DC15a-short,
  title = 	 {Stochastic Dual Coordinate Ascent with Adaptive Probabilities},
  author = 	 {Dominik Csiba and Zheng Qu and Peter Richt\'{a}rik},
  booktitle = 	 {ICML},
  year = 	 {2015}
}

@INPROCEEDINGS {CC20c,
author = {Chen Cui and Ning Yang and Philip S. Yu},
booktitle = {2020 IEEE International Conference on Big Data},
title = {{MLANE}: Meta-Learning Based Adaptive Network Embedding},
year = {2020},
pages = {904-909},
}

@article{JC98a,
author      = {Joseph Czyzyk and Michael P. Mesnier and Jorge J. Mor\'e},
title       = {The {NEOS} {S}erver},
journal     = {IEEE Computational Science \& Engineering},
pages       = {68--75},
volume      = {5},
year        = {1998},
}


@article{LD98a,
    Author = {Dagum, Leonardo and Menon, Ramesh},
    Journal = {IEEE Computational Science and Engineering},
    Pages = {46--55},
    Title = {{OpenMP: an industry standard API for shared-memory programming}},
    Volume = {5},
    Year = {1998}
}

@article{LD98a-short,
    Author = {Dagum, Leonardo and Menon, Ramesh},
    Journal = {IEEE Comput. Sci. Eng.},
    Pages = {46--55},
    Title = {{OpenMP: an industry standard API for shared-memory programming}},
    Volume = {5},
    Year = {1998}
}

@inproceedings{XD22a,
    title = "Revisiting Transformer-based Models for Long Document Classification",
    author = "Dai, Xiang  and
      Chalkidis, Ilias  and
      Darkner, Sune  and
      Elliott, Desmond",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
    year = "2022",
    pages = "7212--7230"
}

@Article{YHD05a,
  author = {Yu-Hong Dai and Roger Fletcher},
  title = {Projected {B}arzilai-{B}orwein methods for large-scale
    box-constrained quadratic programming},
  journal = {Numerische Mathematik},
  year = {2005},
  pages = {21--47},
  volume = {100}
}

@article{YHD06a,
    author    = {Yu-Hong Dai and
        Roger Fletcher},
    title     = {New algorithms for singly linearly constrained quadratic
        programs subject to lower and upper bounds},
    journal   = {Math. Program.},
    volume    = {106},
    number    = {3},
    year      = {2006},
    pages     = {403--421},
    ee        = {http://dx.doi.org/10.1007/s10107-005-0595-2},
    bibsource = {DBLP, http://dblp.uni-trier.de}
}

@inproceedings{BD14a,
 author = {Dalessandro, Brian and Chen, Daizhuo and Raeder, Troy and Perlich, Claudia and Han Williams, Melinda and Provost, Foster},
 title = {Scalable Hands-free Transfer Learning for Online Advertising},
 booktitle = {Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)},
 year = {2014},
 pages = {1573--1582}
} 

@inproceedings{AD18a,
author = {Dalmia, Ayushi and Jawahar, Ganesh and Gupta, Manish},
title = {Towards Interpretation of Node Embeddings},
year = {2018},
doi = {10.1145/3184558.3191523},
booktitle = {Proceedings of the The Web Conference},
pages = {945–952}
}

@incollection{PD08a,
title = {{T}rue{S}kill Through Time: Revisiting the History of Chess},
author = {Pierre Dangauthier and Ralf Herbrich and Tom Minka and Thore Graepel},
booktitle = {Advances in Neural Information Processing Systems 20},
editor = {},
publisher = {MIT Press},
address = {Cambridge, MA},
pages = {},
year = {2008}
}

@Article{JWD73a,
  author = 	 {J. W. Daniel},
  title = 	 {Stability of the solution of
definite quadratic programs},
  journal = 	 {Mathematical Programming},
  year = 	 {1973},
  volume =	 {5},
  number =	 {1},
  pages =	 {41--53}
}

@inproceedings{CD92a,
  title={Learning rate schedules for faster stochastic gradient search},
  author={Darken, Christian and Chang, Joseph and Moody, John},
  booktitle={Proceedings of the IEEE Workshop on Neural Networks for Signal Processing},
  pages={3--12},
  year={1992}
}


@Article{JD72a,
  author = 	 {John N. Darroch and Douglas Ratcliff},
  title = 	 {Generalized iterative scaling for log-linear models},
  journal = 	 {The Annals of Mathematical Statistics},
  year = 	 {1972},
  OPTkey = 	 {},
  volume =	 {43},
  number =	 {5},
  pages =	 {1470--1480},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}


@Article{JD72a-short,
  author = 	 {John N. Darroch and Douglas Ratcliff},
  title = 	 {Generalized iterative scaling for log-linear models},
  journal = 	 {Ann. Math. Statist.},
  year = 	 {1972},
  OPTkey = 	 {},
  volume =	 {43},
  number =	 {5},
  pages =	 {1470--1480},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@INPROCEEDINGS{AD07a,
    author = {Abhinandan Das and Mayur Datar and Shyam Rajaram and Ashutosh Garg},
    title = {Google news personalization: scalable online collaborative filtering},
    booktitle = {Proceedings of the 16th international conference on World Wide Web},
    year = {2007},
    pages = {271--280}
}

@Article{ID04a,
  author = {Daubechies, Ingrid and Defrise, Michel and De Mol, Christine},
  title = {An iterative thresholding algorithm for linear inverse problems with a sparsity constraint},
  journal = {Communications on Pure and Applied Mathematics},
  year = {2004},
  volume = {57},
  pages = {1413--1457}
}

@unpublished{HDI04a,
  author =       {Daum\'e, III, Hal},
  title =        {Notes on {CG} and {LM-BFGS} Optimization of Logistic Regression},
  year =         {2004},
  url = {http://www.cs.utah.edu/~hal/megam/}
}

@article{CD05a,
author	= {Christensen, David},
title	= {Fast algorithms for the calculation of
	{K}endall's $\tau$},
journal	= {Computational Statistics},
volume	= {20},
pages	= {51--62},
year	= {2005}
}

@Book{HAD88a,
  author =	 {Herbert A. David},
  ALTeditor = 	 {},
  title = 	 {The method of paired comparisons},
  publisher = 	 {Oxford University Press},
  year = 	 {1988},
  OPTkey = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  edition =	 {Second},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}
%  address =	 {New York},

@article{ERD89a,
  title={Super-matrix methods},
  author={Davidson, Ernest R.},
  journal={Computer Physics Communications},
  volume={53},
  number={1},
  pages={49--60},
  year={1989},
  publisher={Elsevier}
}

@inproceedings{JD10b,
 author = {Davidson, James and Liebald, Benjamin and Liu, Junning and Nandy, Palash and Van Vleet, Taylor and Gargi, Ullas and Gupta, Sujoy and He, Yu and Lambert, Mike and Livingston, Blake and Sampath, Dasarathi},
 title = {The {Y}ou{T}ube Video Recommendation System},
 booktitle = {Proceedings of the Fourth ACM Conference on Recommender Systems},
 year = {2010},
 pages = {293--296}
}

@inproceedings{JD10b-short,
 author = {Davidson, James and Liebald, Benjamin and Liu, Junning and Nandy, Palash and Van Vleet, Taylor and Gargi, Ullas and Gupta, Sujoy and He, Yu and Lambert, Mike and Livingston, Blake and Sampath, Dasarathi},
 title = {The {Y}ou{T}ube Video Recommendation System},
 booktitle = {RecSys},
 year = {2010}
}

@Article{RRD76a,
  author = 	 {R. R. Davidson and P. H. Farquhar},
  title = 	 {A bibliography on the method of paired comparisons},
  journal = 	 {Biometrics},
  year = 	 {1976},
  OPTkey = 	 {},
  volume =	 {32},
  number =	 {},
  pages =	 {241--252},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}


@article{EFD92,
author      = {E. F. D'Azevedo and P. A. Forsyth and W. P. Tang},
journal     = {BIT},
pages       = {442--463},
title       = {Towards a cost effective {ILU} preconditioner with high
                  level fill},
volume      = {32},
year        = {1992}
}


@article{JD08b,
 author = {Jeffrey Dean and Sanjay Ghemawat},
 title = {Map{R}educe: simplified data processing on large clusters},
 journal = {Communications of the ACM},
 volume = {51},
 number = {1},
 year = {2008},
 pages = {107--113}
 }

@article{JD08b-short,
 author = {Jeffrey Dean and Sanjay Ghemawat},
 title = {Map{R}educe: simplified data processing on large clusters},
 journal = {CACM},
 volume = {51},
 year = {2008},
 pages = {107--113}
 }

@inproceedings{JD12a,
  title={Large Scale Distributed Deep Networks.},
  author={Dean, Jeffrey and Corrado, Greg and Monga, Rajat and Chen, Kai and Devin, Matthieu and Le, Quoc V and Mao, Mark Z and Marc'Aurelio Ranzato and Senior, Andrew W and Tucker, Paul A and others},
  booktitle = {Advances in Neural Information Processing Systems (NIPS) 25},
  year={2012},
  pages = {1223--1231}
}

@Book{LD99a,
  author =	 {Lokenath Debnath and Piotr Mikusinski},
  title = 	 {Introduction to Hilbert Spaces with Applications},
  publisher = 	 {Academic Press},
  year = 	 {1999},
  address =	 {San Diego},
  edition =	 {Second}
}

@article{SD16a,
  author = {Decherchi, Sergio and Rocchia, Walter},
  year = {2016},
  month = {04},
  pages = {1-8},
  title = {Import Vector Domain Description: A Kernel Logistic One-Class Learning Algorithm},
  volume = {28},
  number={7},
  journal = {IEEE Transactions on Neural Networks and Learning Systems},
  doi = {10.1109/TNNLS.2016.2547220}
}

@inproceedings{FD03a,
  author    = {Francesco De Comit{\'e} and
               R{\'e}mi Gilleron and
               Marc Tommasi},
  title     = {Learning Multi-label Alternating Decision Trees from Texts
               and Data.},
  booktitle = {MLDM},
  year      = {2003},
  pages     = {35--49},
}

%  ee        = {http://link.springer.de/link/service/series/0558/bibs/2734/27340035.htm},
%  crossref  = {DBLP:conf/mldm/2003},
%  bibsource = {DBLP, http://dblp.uni-trier.de}
%

@inproceedings{DD00a,
 author = {Dennis DeCoste and Kiri Wagstaff},
 title = {Alpha seeding for support vector machines},
 booktitle = {Proceedings of the Sixth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining},
 year = {2000},
 pages = {345--349}
 }

@inproceedings{DD00a-short,
 author = {Dennis DeCoste and Kiri Wagstaff},
 title = {Alpha seeding for support vector machines},
 booktitle = {KDD},
 year = {2000}
 }


@Article{DD01a,
  author = 	 {Dennis DeCoste and Bernhard Sch\"{o}lkopf},
  title = 	 {Training
Invariant Support Vector Machines},
  journal = 	 {Machine Learning},
  year = 	 {2002},
  volume={46},
  pages={161--190}
}

@inproceedings{AD14a,
  title={S{AGA}: A fast incremental gradient method with support for non-strongly convex composite objectives},
  author={Defazio, Aaron and Bach, Francis and Lacoste-Julien, Simon},
  booktitle={Advances in Neural Information Processing Systems},
  pages={1646--1654},
  year={2014}
}

@inproceedings{AD14a-short,
  title={S{AGA}: A fast incremental gradient method with support for non-strongly convex composite objectives},
  author={Defazio, Aaron and Bach, Francis and Lacoste-Julien, Simon},
  booktitle={NIPS},
  year={2014}
}


@article{JED77a,
	title={Quasi-{N}ewton methods, motivation and theory},
	author={Dennis, Jr, John E. and Mor{\'e}, Jorge J.},
	journal={SIAM Review},
	volume={19},
	number={1},
	pages={46--89},
	year={1977},
	publisher={SIAM}
}

@article{SD90a,
  title={Indexing by latent semantic analysis},
  author={Scott Deerwester and 
Susan T. Dumais and George W. Furnas and
Thomas K. Landauer and Richard Harshman},
  journal={Journal of the American Society for Information Science},
  volume={41},
  number={6},
  pages={391--407},
  year={1990}
}

@InProceedings{OD04a,
  author = {Ofer Dekel and Joseph Keshet and Yoram Singer},
  title = {Large Margin Hierarchical Classification},
  booktitle = {ICML},
  year = {2004}
}

@article{OD12a,
        author = {Ofer Dekel and Ran Gilad-Bachrach and Ohad Shamir and Lin Xiao},
        title = {Optimal Distributed Online Prediction Using Mini-Batches},
        journal = {Journal of Machine Learning Research},
        volume = {13},
        year = {2012},
        pages = {165--202}
}

@inproceedings{KD10a,
author = {Dembczy\'{n}ski, Krzysztof and Cheng, Weiwei and H\"{u}llermeier, Eyke},
title = {Bayes optimal multilabel classification via probabilistic classifier chains},
year = {2010},
booktitle = {Proceedings of the 27th International Conference on Machine Learning},
pages = {279--286}
}

@article{RSD82a,
author = {Dembo, Ron S. and Eisenstat, Stanley C. and Steihaug, Trond},
year = {1982},
pages = {400-408},
title = {Inexact {N}ewton Methods},
volume = {19},
journal     = {SIAM Journal on Numerical Analysis}
}

@article{RSD82a-short,
author = {Dembo, Ron S. and Eisenstat, Stanley C. and Steihaug, Trond},
year = {1982},
pages = {400-408},
title = {Inexact {N}ewton Methods},
volume = {19},
journal     = {SIAM J. Numer. Anal.},
}

@TechReport{RSD83a,
  author = 	 {Ron S. Dembo and Ulrich Tulowitzki},
  title = 	 {On the minimization of quadratic functions subject to box constraints},
  institution =  {School of Organization and Management, Yale University},
  year = 	 {1983},
  type =	 {Working paper series},
  number =	 {B71}
}


@TechReport{RSD83a-short,
  author = 	 {Ron S. Dembo and  Ulrich Tulowitzki},
  title = 	 {On the minimization of quadratic functions subject to box constraints},
  institution =  {Yale University},
  year = 	 {1983}
}

@article{RSD83b,
  title={Truncated {N}ewton algorithms for large-scale unconstrained optimization},
  author={Dembo, Ron S. and Steihaug, Trond},
  journal={Mathematical Programming},
  volume={26},
  pages={190--212},
  year={1983}
}

@misc{AD16a,
  title={Fast model selection by limiting {SVM} training times},
  author={Demircioglu, Aydin and Horn, Daniel and Glasmachers, Tobias and Bischl, Bernd and Weihs, Claus},
  year={2016},
  doi = {10.48550/ARXIV.1602.03368},
  url = {https://arxiv.org/abs/1602.03368},
  publisher = {arXiv}
}

@article{APD77a,
  title={{Maximum likelihood from incomplete data via the EM algorithm}},
  author={Demster, AP and Laird, NM and Rubin, DB},
  journal={Journal of the Royal Statistical Society B},
  volume={39},
  pages={1--38},
  year={1977}
}

@inproceedings{DD20a,
    title = "{G}o{E}motions: A Dataset of Fine-Grained Emotions",
    author = "Demszky, Dorottya  and
      Movshovitz-Attias, Dana  and
      Ko, Jeongwoo  and
      Cowen, Alan  and
      Nemade, Gaurav  and
      Ravi, Sujith",
    booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics",
    year = "2020",
    doi = "10.18653/v1/2020.acl-main.372",
    pages = "4040--4054"
}

@inproceedings{TD09a,
 author = {Denning, Tamara and Andrew, Adrienne and Chaudhri, Rohit and Hartung, Carl and Lester, Jonathan and Borriello, Gaetano and Duncan, Glen},
 title = {{BALANCE}: towards a usable pervasive wellness application with accurate activity inference},
 booktitle = {Proceedings of the 10th workshop on Mobile Computing Systems and Applications},
 series = {HotMobile '09},
 year = {2009},
 isbn = {978-1-60558-283-2},
 location = {Santa Cruz, California},
 pages = {5:1--5:6},
 articleno = {5},
 numpages = {6},
 url = {http://doi.acm.org/10.1145/1514411.1514416},
 doi = {10.1145/1514411.1514416},
 acmid = {1514416},
 publisher = {ACM},
 address = {New York, NY, USA},
} 

@incollection{JED94,
   author = {J. E. Dennis and L. N. Vicente},
   title = {Trust-region interior-point algorithms for minimization
            problems with simple bounds},
   booktitle = {Applied Mathematics and Parallel
	        Computing, Festschrift for Klaus Ritter},
   pages = {97--107},
   editor = {H. Fisher and B. Riedm\"uller and S. Sch\"affler},
   publisher = {{Physica--Verlag, Springer--Verlag}},
   year = {1996} 
}

@inproceedings{RD14a,
author = {Devooght, Robin and Mantrach, Amin and Kivim\"{a}ki, Ilkka and Bersini, Hugues and Jaimes, Alejandro and Saerens, Marco},
title = {Random Walks Based Modularity: Application to Semi-Supervised Learning},
year = {2014},
booktitle = {Proceedings of the 23rd International Conference on World Wide Web (WWW)},
pages = {213--224}
}

@inproceedings{RD15a,
  title={Dynamic matrix factorization with priors on unknown values},
  author={Devooght, Robin and Kourtellis, Nicolas and Mantrach, Amin},
  booktitle={Proceedings of the 21th ACM SIGKDD international conference on knowledge discovery and data mining (KDD)},
  pages={189--198},
  year={2015}
}

@inproceedings{RD15a-short,
  title={Dynamic matrix factorization with priors on unknown values},
  author={Devooght, Robin and Kourtellis, Nicolas and Mantrach, Amin},
  booktitle={KDD},
  year={2015}
}

@inproceedings{JD19a,
  author    = {Jacob Devlin and
               Ming-Wei Chang and
               Kenton Lee and
               Kristina Toutanova},
  editor    = {Jill Burstein and
               Christy Doran and
               Thamar Solorio},
  title     = {{BERT:} Pre-training of Deep Bidirectional Transformers for Language
               Understanding},
  booktitle = {Proceedings of the 2019 Conference of the North American Chapter of
               the Association for Computational Linguistics: Human Language Technologies,
               {NAACL-HLT}},
  pages     = {4171--4186},
  year = {2019},
  doi       = {10.18653/v1/n19-1423}
}

@article{ID01a,
  title={Concept decompositions for large sparse text data using clustering},
  author={Dhillon, Inderjit S. and Modha, Dharmendra S.},
  journal={Machine learning},
  volume={42},
  pages={143--175},
  year={2001}
}

@article{JKD94,
author      = {J. K. Dickinson and P. A. Forsyth},
journal     = {Int. J. Num. Meth. Eng.},
pages       = {2211--2234},
title       = {Preconditioned conjugate gradient methods for
                  three-dimensional linear elasticity},
volume      = {37},
year        = {1994}
}


@InCollection{GD94a,
  author = 	 {Di Pillo, G.},
  title = 	 {Exact penalty methods},
  booktitle = 	 {Algorithms for Continuous Optimization},
  year =	 {1994},
  editor =	 {Il Ciocco},
  publisher =	 {Kluwer Acad. Publ.},
  address =	 {Dordrecht}

}

@article{TGD95a,
    author = "Thomas G. Dietterich and Ghulum Bakiri",
    title = "Solving Multiclass Learning Problems via Error-Correcting Output Codes",
    journal = "Journal of Artificial Intelligence Research",
    volume = "2",
    pages = "263--286",
    year = "1995",
}

@article{TGD95a-short,
    author = "Thomas G. Dietterich and Ghulum Bakiri",
    title = "Solving Multiclass Learning Problems via Error-Correcting Output Codes",
    journal = "J. Artificial Intelligence Res.",
    volume = "2",
    pages = "263--286",
    year = "1995",
}

@article{TGD98a,
author = {Dietterich, T. G.},
title   = {An experimental comparison of three methods for contructing
           ensembles of decision trees: {B}agging, boosting, and randomization},
journal = {Machine Learning},
year    = {1998},
volume  = {40},
number  = {2},
pages   = {139--158}
}



@inproceedings{CD16a,
  author    = {Djork{-}Arn{\'{e}} Clevert and
               Thomas Unterthiner and
               Sepp Hochreiter},
  title     = {Fast and Accurate Deep Network Learning by Exponential Linear Units
               ({ELU}s)},
  booktitle = {Proceedings of the Fourth International Conference on Learning Representations (ICLR)},
  year      = {2016}
}

@inproceedings{CD16a-short,
  author    = {Djork{-}Arn{\'{e}} Clevert and
               Thomas Unterthiner and
               Sepp Hochreiter},
  title     = {Fast and Accurate Deep Network Learning by Exponential Linear Units
               ({ELU}s)},
  booktitle = {ICLR},
  year      = {2016}
}

@article{HD20a,
  author = {Dong, Hang and Su\'{a}rez-Paniagua, Víctor and Whiteley, William and Wu, Honghan},
  year = {2021},
  pages = {103728},
  title = {Explainable Automated Coding of Clinical Notes using Hierarchical Label-wise Attention Networks and Label Embedding Initialisation},
  volume = {116},
  journal = {Journal of Biomedical Informatics},
  doi = {10.1016/j.jbi.2021.103728}
}

@article{JJD88a,
 author = {Dongarra, Jack J. and Du Croz, Jeremy and Hammarling, Sven and Hanson, Richard J.},
 title = {An extended set of {F}ortran basic linear algebra subprograms},
 journal = {ACM Transactions on Mathematical Software},
 volume = {14},
 number = {1},
 year = {1988},
 pages = {1--17}
} 

@article{JJD88a-short,
 author = {Dongarra, Jack J. and Du Croz, Jeremy and Hammarling, Sven and Hanson, Richard J.},
 title = {An extended set of {F}ortran basic linear algebra subprograms},
 journal = {ACM TOMS},
 volume = {14},
 year = {1988},
 pages = {1--17}
} 

@article{JJD90a,
 author = {Dongarra, Jack J. and Du Croz, Jeremy and Hammarling, Sven  and Duff, Iain S.},
 title = {A Set of Level 3 Basic Linear Algebra Subprograms},
 journal = {ACM Transactions on Mathematical Software},
 volume = {16},
 number = {1},
 year = {1990},
 pages = {1--17}
}

@article{JJD90a-short,
 author = {Dongarra, J. J. and Du Croz, Jeremy and Hammarling, Sven and Duff, Iain S.},
 title = {A Set of Level 3 Basic Linear Algebra Subprograms},
 journal = {ACM TOMS}, 
 volume = {16},
 year = {1990},
 pages = {1--17}
} 

@incollection {DD04a,
  author = "David Donoho and  Victoria Stodden",
  title = "When Does Non-Negative Matrix Factorization Give a Correct Decomposition into Parts?",
  booktitle = "Advances in Neural Information Processing Systems 16",
  editor = "Sebastian Thrun and Lawrence Saul and Bernhard {Sch\"{o}lkopf}",
  publisher = "MIT Press",
  address = "Cambridge, MA",
  year = "2004",
  keywords = "image databases, non-negative matrix factorization",
  }

@incollection {DD04a-short,
  author = " David Donoho and  Victoria Stodden",
  title = " When Does Non-Negative Matrix Factorization Give a Correct Decomposition into Parts?",
  booktitle = "{NIPS} 16",
  year = "2004"
  }

@Article{DLD08a,
  author = {David L. Donoho and Yaakov Tsaig},
  title = {Fast Solution of L1 Minimization
Problems When the Solution May Be Sparse},
  journal = {IEEE Transactions on Information
Theory},
  year = {2008},
  pages = {4789--4812},
  volume = {54}
}
%  url = {http://www-stat.stanford.edu/~donoho/Reports/2006/kstep-20061005.pdf},


@article{KCD10a,
  title={{BDVal: reproducible large-scale predictive model development and validation in high-throughput datasets}},
  author={Kevin C. Dorff and Nyasha Chambwe and
Marko Srdanovic and Fabien Campagne},
  journal={Bioinformatics},
  volume={26},
  number={19},
  pages={2472--2473},
  year={2010},
  publisher={Oxford Univ Press}
}
%  issn={1367-4803},

@article{PD05a,
 author = {Drineas, Petros and Mahoney, Michael W.},
 title = {On the {Nystr\"{o}m} Method for Approximating a Gram Matrix for Improved Kernel-based Learning},
 journal = {Journal of Machine Learning Research},
 volume = {6},
 pages = {2153--2175},
 year = {2005}
}

@inproceedings{GD11a, 
  author = {Gideon Dror and Noam Koenigstein and Yehuda Koren and Markus Weimer}, 
  title = 	 {The {Y}ahoo! Music Dataset and {KDD}-{C}up 11},
  booktitle = 	 {JMLR Workshop and Conference Proceedings: Proceedings of KDD Cup 2011},
  OPTcrossref =  {},
  OPTkey = 	 {},
  pages =	 {3--18},
  year =	 {2012},
  OPTeditor = 	 {},
  volume =	 {18},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTaddress = 	 {},
  OPTmonth = 	 {},
  OPTorganization = {},
  OPTpublisher = {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@article{YD14a,
  title={Performance of first-order methods for smooth convex minimization: a novel approach},
  author={Drori, Yoel and Teboulle, Marc},
  journal={Mathematical Programming},
  volume={145},
  pages={451--482},
  year={2014}
}

@conference{CD09a,
  title={Replicability is not reproducibility: Nor is it good science},
  author={Drummond, C.},
  booktitle={Proceedings of the Evaluation Methods for Machine Learning Workshop at the 26th ICML},
  year={2009}
}

@misc{DD16a,
	title={Error bounds, quadratic growth, and linear convergence of
		proximal methods},
	author={Drusvyatskiy, Dmitriy and Lewis, Adrian S},
	note={arXiv preprint arXiv:1602.06661},
	year={2016}
}

@Article{KD02a,
  author = 	 {K. Duan and S. S. Keerthi and A. N. Poo},
  title = 	 {Evaluation of simple
     performance measures for tuning {SVM} hyperparameters},
  journal = 	 {Neurocomputing},
  year = 	 {2003},
  volume={51},
  pages={41--59}
}


@TechReport{KD03a,
  author =	 {Kaibo Duan and S. Sathiya Keerthi},
  title =	 {Which is the Best Multiclass {SVM} Method? {A}n Empirical Study},
  year =	 {2003},
  institution =  {Control Division, 
Department of Mechanical Engineering, National University of Singapore},
  number =	 {CD-03-12}
}

@article{MD04a,
author = "Duarte, M. and Hu, Y. H.",
title = "Vehicle Classification in Distributed Sensor Networks",
journal = "Journal of Parallel and Distributed Computing",
volume = "64",
number = "7",
month = jul,
year = 2004,
pages = "826--838"}

@misc{AD21a,
  title={Test Set Sizing Via Random Matrix Theory},
  author={Dubbs, Alexander},
  note={arXiv preprint arXiv:2112.05977},
  year={2021}
}

@inproceedings{JD08a,
  author = {John Duchi and Shai Shalev-Shwartz and Yoram Singer and
Tushar Chandra},
  title = {Efficient projections onto the {L}1-ball for learning in
high dimensions},
  booktitle = {Proceedings of the Twenty Fifth International
Conference on Machine Learning (ICML)},
  year = {2008}
}
%   pages = {272--279}

@inproceedings{JD09a,
  author = {John Duchi and Yoram Singer},
  title = {Boosting with Structural Sparsity},
  booktitle = {Proceedings of the Twenty Sixth International Conference
on Machine Learning (ICML)},
  year = {2009}
}

@article{JD09b,
 author = {Duchi, John and Singer, Yoram},
 title = {Efficient Online and Batch Learning Using Forward Backward Splitting},
 journal = {Journal of Machine Learning Research},
 volume = {10},
 pages = {2899--2934},
 year = {2009}
}

@article{JD10a,
 author = {Duchi, John and Hazan, Elad and Singer, Yoram},
 title = {Adaptive Subgradient Methods for Online Learning and
Stochastic Optimization},
 journal = {Journal of Machine Learning Research},
 volume = {12},
 year = {2011},
 pages = {2121--2159}
}

@article{JD10a-short,
 author = {Duchi, John and Hazan, Elad and Singer, Yoram},
 title = {Adaptive Subgradient Methods for Online Learning and
Stochastic Optimization},
 journal = {JMLR},
 volume = {12},
 year = {2011},
 pages = {2121--2159}
}

@inproceedings{MD04b,
 author =  {Miroslav Dud\'{i}k and Steven J. Phillips  and Robert E. Schapire},
 title =   {Performance guarantees for regularized maximum entropy
density estimation},
  booktitle = "Proceedings of the 17th Annual Conference on
Computational Learning Theory",
  pages = "655--662",
  year = "2004"
}


@inproceedings{MD11a,
 author = {Dud\'{\i}k, Miroslav and Langford, John and Li, Lihong},
 title = {Doubly Robust Policy Evaluation and Learning},
 booktitle = {Proceedings of the 28th International Conference on International Conference on Machine Learning (ICML)},
 year = {2011},
 pages = {1097--1104}
}

@inproceedings{MD11a-short,
title={Doubly robust policy evaluation and learning},
author={Dud\'{\i}k, Miroslav and Langford, John and Li, Lihong},
booktitle={ICML},
year={2011}
}

@article{STD98a,
  title={Inductive learning algorithms and representations for text categorization},
  author={Dumais, S. and Platt, J. and Heckerman, D. and Sahami, M.},
  journal={Proceedings of the Seventh International Conference on Information and Knowledge Management},
  volume={11},
  pages={16},
  year={1998},
  publisher={Maryland: Association for Computing Mac}
}

@inproceedings{STD00a,
    author = "Susan T. Dumais and Hao Chen",
    title = "Hierarchical classification of {W}eb content",
    booktitle = "Proceedings of {SIGIR}-00, 23rd {ACM} International Conference on Research and Development in Information Retrieval",
    publisher = "ACM Press, New York, US",
    address = "Athens, GR",
    editor = "Nicholas J. Belkin and Peter Ingwersen and Mun-Kew Leong",
    pages = "256--263",
    year = "2000",
    url = "citeseer.ist.psu.edu/dumais00hierarchical.html" 
}

@inproceedings{STD00a-short,
    author = "Susan T. Dumais and Hao Chen",
    title = "Hierarchical classification of {W}eb content",
    booktitle = "SIGIR",
    pages = {256--263},
    year = "2000"}


@Misc{LD00a,
  author =	 {L. D{\"u}mbgen},
  title =	 {Statistical software (MATLAB)},
  year =	 {2000},
  note =	 {Available at
{\tt http://www.math.mu-luebeck.de/workers/duembgen/software/software.html}
}
}



@article{ISD89a,
author      = {Iain S. Duff and Roger G. Grimes and John G. Lewis},
journal     = {ACM Transactions on  Mathematical Software},
pages       = {1--14},
title       = {Sparse matrix test problems},
volume      = {15},
year        = {1989}
}
% note       = {Currently available in {\bf http://math.nist.gov/MatrixMarket}} 

@article{ISD89a-short,
author      = {Duff, I. S. and Grimes, R. G. and Lewis, J. G.},
journal     = {ACM TOMS},
pages       = {1--14},
title       = {Sparse matrix test problems},
volume      = {15},
year        = {1989}
}

@article{ISD89b,
author      = {I. S. Duff and G. A. Meurant},
journal     = {BIT},
title       = {The effect of ordering on preconditioned conjugate
                  gradients},
volume      = {29},
pages       = {635--657},
year        = {1989}
}


@article{ISD02a,
 author = {Duff, Iain S. and Heroux, Michael A. and Pozo, Roldan},
 title = {An Overview of the Sparse Basic Linear Algebra Subprograms: The New Standard from the BLAS Technical Forum},
 journal = {ACM Transactions on Mathematical Software},
 volume = {28},
 number = {2},
 year = {2002},
 pages = {239--267}
}

@Article{JCD79a,
  author = 	 "Joseph C. Dunn",
  title = 	 "Rates of convergence for conditional gradient algorithms near singular and nonsingular extremals",
  journal     = {SIAM J. Control Optim.},		  
  year =	 "1979",
  volume =	 "17",
  number =	 "2",
  pages =	 "187--211"
}


@article{JCD80a,
        author={Joseph C. Dunn},
        journal={SIAM Journal on Control and Optimization},
        title={{N}ewton's method and the {G}oldstein step length rule for constrained minimization},
        year={1980},
        volume={18},
        issue={6},
        pages={659--674}
}
		  
@Article{JCD81a,
  author = 	 "Joseph C. Dunn",
  title = 	 "Global and asymptotic convergence rate estimates for 
		  a class of projected gradient processes",
  journal     = {SIAM J. Control Optim.},		  
  year =	 "1981",
  volume =	 "19",
  number =	 "3",
  pages =	 "368--400"
}

@article{JCD87,
author      = {Joseph C. Dunn},
journal     = {J. Optim. Theory Appl.},
pages       = {203--216},
title       = {On the convergence of projected gradient processes to singular critical points},
volume      = {55},
year        = {1987}
}

@inproceedings{AGD17a,
author = {Garc\'{\i}a-Dur\'{a}n, Alberto and Niepert, Mathias},
title = {Learning Graph Representations with Embedding Propagation},
year = {2017},
booktitle = {Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS)},
pages = {5125--5136}
}

@Article{du:an89,
  author = 	 {R. Durbin and R. Szeliski and A. L. Yuille},
  title = 	 {An analysis of the elastic net approach to the travelling 
                  salesman problem},
  journal = 	 {Neural Computation},
  year = 	 {1989},
  volume =	 {1},
  pages =	 {348--358}
}

@Article{du:an,
  author = 	 {R. Durbin and D. Willshaw},
  title = 	 {An Analogue Approach of the Travelling Salesman
                  Problem Using an Elastic Net Method},
  journal = 	 {Nature},
  year = 	 {1987},
  volume =	 {326},
  pages =	 {689--691}
}



@Article{OD60a,
  author = 	 {O. Dykstra},
  title = 	 {Rank analysis of incomplete block designs: a method of paired comparisons employing unequal repetitions on pairs},
  journal = 	 {Biometrics},
  year = 	 {1960},
  OPTkey = 	 {},
  volume =	 {16},
  OPTnumber = 	 {},
  pages =	 {176--188},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@Article{AE93a,
  author = 	 {A. Edelman},
  title = 	 {Large dense numerical linear algebra in 1993: {T}he parallel computing influence},
  journal = 	 {International J. Supercomputer Appl.},
  year = 	 {1993},
  volume =	 {7},
  pages =	 {113--128}
}



@InProceedings{AE94a,
  author = 	 {A. Edelman},
  title = 	 {Large Numerical Linear Algebra in 1994: The Continuing Influence of Parallel Computing},
  booktitle = 	 {Proceedings of the 1994 Scalable High Performance Computing Conference},
  year =	 {1994},
  publisher =	 {IEEE Computer Society Press},
  pages =	 {781--787}
}

@book{BE82a,
    author = {B. Efron},
    title={The Jackknife, the Bootstrap and Other Resampling Plans},
    publisher ={Bristol: Arrowsmith},
    year = "1982"
}

@Article{BE83a,
  author = 	 {B. Efron},
  title = 	 {Estimating the Error Rate of a Prediction Rule: Improvement on Cross-Validation},
  journal = 	 {Journal of the American Statistical Association},
  year = 	 {1983},
  volume =	 {78},
  number =	 {382},
  pages =	 {316--331},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@article{BE83b,
  title={A leisurely look at the bootstrap, the jackknife, and cross-validation},
  author={Bradley Efron and Gail Gong},
  journal={American Statistician},
  pages={36--48},
  year={1983}
}

@Article{BE04a,
  author = {Bradley Efron and Trevor Hastie and Iain Johnstone and
Robert Tibshirani},
  title = {Least Angle Regression},
  journal = {Annals of Statistics},
  year = {2004},
  volume = {32},
  pages = {407--499}
}


@article{VE91,
author      = {V. Eijkhout},
journal     = {Linear Algebra Appl.},
title       = {Analysis of parallel incomplete point factorizations},
volume      = {154--156},
pages       = {723--740},
year        = {1991}
}

@article{SCE94a,
    author = {Stanley C. Eisenstat and Homer F. Walker},
    title = {Globally Convergent Inexact Newton Methods},
    journal = {SIAM Journal on Optimization},
    volume = {4},
    number = {2},
    pages = {393-422},
    year = {1994},
}

@article{SCE96a,
  title={Choosing the forcing terms in an inexact {N}ewton method},
  author={Eisenstat, Stanley C. and Walker, Homer F.},
  journal={SIAM Journal on Scientific Computing},
  volume={17},
  number={1},
  pages={16--32},
  year={1996}
}


@article{SCE96a-short,
  title={Choosing the forcing terms in an inexact {N}ewton method},
  author={Eisenstat, Stanley C. and Walker, Homer F.},
journal     = "SIAM J. Sci. Comput.",  
  volume={17},
  number={1},
  pages={16--32},
  year={1996}
}

@article{ME17a,
  title = {Converting {SVDD} scores into probability estimates: Application to outlier detection},
  journal = {Neurocomputing},
  volume = {268},
  pages = {64--75},
  year = {2017},
  author = {Meriem {El Azami} and Carole Lartizien and St\'ephane Canu}
}

@Article{ASE96a,
  author = 	 {A. S. El-Bakry and R. A. Tapia and T. Tsuchiya and Y. Zhang},
  title = 	 {On the formulation and theory of the {N}ewton interior-point method for nonlinear programming},
  journal = 	 {J. Optim. Theory Appl.},
  year = 	 {1996},
  volume =	 {89},
  number =	 {3},
  pages =	 {507--541},
}

@techReport{LE10a,
    author = {{El Ghaoui}, Laurent and Viallon, Vivian and Rabbani, Tarek},
    title = {Safe Feature Elimination in Sparse Supervised Learning},
    institution = {EECS Department, University of California, Berkeley},
    year = {2010}
}

@article{LE99a,
  title={A Procrustes problem on the {S}tiefel manifold},
  author={Eld{\'e}n, Lars and Park, Haesun},
  journal={Numerische Mathematik},
  volume={82},
  number={4},
  pages={599--619},
  year={1999}
}

@inproceedings{AME15a,
title={A multi-view deep learning approach for cross domain user modeling in recommendation systems},
author={Elkahky, Ali Mamdouh and Song, Yang and He, Xiaodong},
booktitle={Proceedings of the 24th International Conference on World Wide Web (WWW)},
pages={278--288},
year={2015}
}

@inproceedings{AME15a-short,
title={A multi-view deep learning approach for cross domain user modeling in recommendation systems},
author={Elkahky, Ali Mamdouh and Song, Yang and He, Xiaodong},
booktitle={WWW},
year={2015}
}

@Book{IE76a,
  author =	 {Ivar Ekeland and Roger Temam.        },
  title = 	 {Convex Analysis and Variational Problems},
  publisher = 	 {North-Holland},
  year = 	 {1976},
  address =	 {Amsterdam}
}

@incollection{AE02,
  author =	{A. Elisseeff and M. Pontil},
  title =	{Leave-one-out Error and Stability of Learning Algorithms with Applications},
  booktitle =	{Learning Theory and Practice},
  publisher =	{IOS Press},
  year =	{2002},
  editor =	{J. Suykens and and G. Horvath and S. Basu and C. Micchelli and J. Vandewalle},
  address = {Amsterdam; Washington, DC},
  series =	{NATO ASI Series}
}

@inproceedings{AE02a,
title = "A kernel method for multi-labelled classification"
,author = "Andr\'e Elisseeff and Jason Weston"
,year = 2002
,booktitle = "Advances in Neural Information Processing Systems 14"
,editor = "Thomas G. Dietterich and Susan Becker and Zoubin Ghahramani"
,keywords = "classification, multilabel, text, svm"
}

@inproceedings{AE02a-short,
title = "A kernel method for multi-labelled classification"
,author = "Andr\'e Elisseeff and Jason Weston"
,year = 2002
,booktitle = "{NIPS} 14"
}


@inproceedings{CE03a,
author = {Elkan, Charles},
title = {Using the triangle inequality to accelerate k-means},
year = {2003},
booktitle = {Proceedings of the Twentieth International Conference on International Conference on Machine Learning (ICML)},
pages = {147--153}
}

@Book{AEE86a,
  author = 	 {Elo, Arpad E.},
  title = 	 {The Rating of Chessplayers, Past and Present},
  publisher = 	 {Arco Publishing},
  year = 	 {1986},
  OPTkey = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  address = 	 {New York},
  edition = 	 {2nd},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@Book{AEE86a-short,
  author = 	 {Elo, Arpad E.},
  title = 	 {The Rating of Chessplayers, Past and Present},
  publisher = 	 {Arco Pub.},
  year = 	 {1986},
  OPTkey = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  edition = 	 {2nd},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@book{CKE10a,
title={Applied missing data analysis},
author={Enders, Craig K.},
year={2010},
publisher={Guilford press}
}

@Article{SME16a,
author = {Erfani, Sarah M. and Rajasegarar, Sutharshan and Karunasekera, Shanika and Leckie, Christopher},
title = {High-dimensional and large-scale anomaly detection using a linear one-class {SVM} with deep learning},
journal = {Pattern Recognition},
volume = {58},
pages = {121--134},
year = {2016}
}

@inproceedings{PAE22a,
author = {Etter, Philip A. and Zhong, Kai and Yu, Hsiang-Fu and Ying, Lexing and Dhillon, Inderjit},
title = {Enterprise-Scale Search: Accelerating Inference for Sparse Extreme Multi-Label Ranking Trees},
year = {2022},
booktitle = {Proceedings of the ACM Web Conference},
pages = {452--461}
}

@Article{TE00a,
  author = 	 {T. Evgeniou and M. Pontil and T. Poggio},
  title = "Regularization Networks and Support Vector Machines",
  journal = 	 {Advances in Computational Mathematics},
  year = 	 {2000},
  volume =	 {13},
  pages =	 {1--50},
  url = "http://citeseer.nj.nec.com/evgeniou00regularization.html" 
}


@article{TE02,
  author =	{T. Evgeniou and M. Pontil and A. Elisseeff},
  title =	{Leave-one-out Error, Stability, and Generalization of Voting Combinations of Classifiers},
  journal =	{Machine Learning},
  year =	{2002},
  note =	{To appear}
}


@article{FF95a,
  title={{Minimization of SC1 functions and the Maratos effect}},
  author={Facchinei, Francisco},
  journal={Operations Research Letters},
  volume={17},
  number={3},
  pages={131--138},
  year={1995}
}

@article{FF95a-short,
  title={{Minimization of SC1 functions and the Maratos effect}},
  author={Facchinei, Francisco},
  journal = {Oper. Res. Lett.},	  
  volume={17},
  pages={131--138},
  year={1995}
}

@book{FF03a,
  title={Finite-dimensional variational inequalities and complementarity problems},
  author={Facchinei, Francisco and Pang, Jong-Shi},
  year={2003},
  publisher={Springer}
}

@inproceedings{EF18a,
  author    = {Evgheniy Faerman and
               Felix Borutta and
               Kimon Fountoulakis and
               Michael W. Mahoney},
  title     = {{LASAGNE:} Locality and Structure Aware Graph Node Embedding},
  booktitle = {Proceedings of {IEEE/WIC/ACM} International Conference on Web Intelligence (WI)},
  pages     = {246--253},
  year      = {2018},
  doi       = {10.1109/WI.2018.00-83}
}

@InProceedings{MF20a,
  title = {Faster Graph Embeddings via Coarsening},
  author = {Fahrbach, Matthew and Goranci, Gramoz and Peng, Richard and Sachdeva, Sushant and Wang, Chi},
  booktitle = {Proceedings of the 37th International Conference on Machine Learning (ICML)},
  pages = {2953--2963},
  year = {2020}
}

@article{MF15b,
  title={Fast linear {SVM} validation based on early stopping in iterative learning},
  author={Famouri, Mahmoud and Taheri, Mohammad and Azimifar, Zohreh},
  journal={International Journal of Pattern Recognition and Artificial Intelligence},
  volume={29},
  number={08},
  pages={1551013},
  year={2015}
}

@inproceedings{JYF01a,
  title={A new trust region algorithm with trust region radius converging to zero},
  author={Fan, Jin-yan and Yuan, Ya-xiang},
  booktitle={Proceeding of the 5th International Conference on Optimization: Techiniques and Applications},
  pages={786--794},
  year={2001}
}

@Article{REF05a,
  author = 	 {Rong-En Fan and Pai-Hsuen Chen and Chih-Jen Lin},
  title = 	 {Working Set Selection Using Second Order Information for Training {SVM}},
  year = 	 {2005},
  url =	 {http://www.csie.ntu.edu.tw/~cjlin/papers/quadworkset.pdf},
  journal = {Journal of Machine Learning Research},
volume      = {6},
pages       = {1889--1918},
  OPTkey = 	 {},
  OPTtype = 	 {},
  OPTnumber = 	 {},
  OPTaddress = 	 {},
  OPTmonth = 	 {},
  OPTannote = 	 {}
}

@Article{REF05a-short,
  author = 	 {Rong-En Fan and Pai-Hsuen Chen and Chih-Jen Lin},
  title = 	 {Working Set Selection Using Second Order Information for Training {SVM}},
  year = 	 {2005},
  journal = {JMLR},
volume      = {6},
pages       = {1889--1918},
  OPTkey = 	 {},
  OPTtype = 	 {},
  OPTnumber = 	 {},
  OPTaddress = 	 {},
  OPTmonth = 	 {},
  OPTannote = 	 {}
}

@techreport{REF07a,
  title={A study on threshold selection for multi-label classification},
  author={Fan, Rong-En and Lin, Chih-Jen},
  institution =  {Department of Computer Science, National Taiwan University},
  year={2007}
}

@Article{REF08a,
  author = 	 {Rong-En Fan and Kai-Wei Chang and Cho-Jui Hsieh and Xiang-Rui Wang and Chih-Jen Lin},
  title = 	 {{LIBLINEAR}: a library for large linear classification},
  journal = 	 {Journal of Machine Learning Research},
  year = 	 {2008},
  OPTkey = 	 {},
  volume =	 {9},
  OPTnumber = 	 {},
  pages =	 {1871--1874},
  url =	 {http://www.csie.ntu.edu.tw/~cjlin/papers/liblinear.pdf},
  OPTmonth = 	 {},
  OPTannote = 	 {}
}


@Article{REF08a-short,
  author = 	 {Rong-En Fan and Kai-Wei Chang and Cho-Jui Hsieh and Xiang-Rui Wang and Chih-Jen Lin},
  title =    {{LIBLINEAR}: a Library for Large Linear Classification},
  journal = {JMLR},
  year =   {2008},
  volume =   {9},
  pages =  {1871--1874}
}

@inproceedings{PF21a,
author = {Peng Fang and Fang Wang and Zhan Shi and Hong Jiang and Dan Feng and Lei Yang},
 title = {Hu{GE}: An Entropy-driven Approach to Efficient and Scalable Graph Embeddings},
 booktitle = {Proceedings of the 37th IEEE International Conference on Data Engineering (ICDE)},
 pages    = {2045--2050}, 
 year = {2021}
}

@Article{SCF01a,
  author = 	 {Shu-Cherng Fang and
Chih-Jen Lin and Soon-Yi Wu},
  title = 	 {Solving 
Quadratic Semi-Infinite Programming Problems by Using
Relaxed Cutting Plane Scheme},
  journal = 	 {Journal of Computational and Applied Mathematics},
  year = 	 {2001},
  volume =	 {129},
  pages =	 {89-104}
}


@TechReport{YHF24a,
  author = {Yu-Hsueh Fang and He-Zhe Lin and Jie-Jyun Liu and Chih-Jen Lin},
  title = 	 {A Step-by-step Introduction to the Implementation of Automatic Differentiation},
  institution =  {Department of Computer Science, National Taiwan University},
  year={2024},
  OPTkey = 	 {},
  OPTtype = 	 {},
  OPTnumber = 	 {},
  OPTaddress = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@article{GF09a,
	title={A nonmonotone truncated {N}ewton--{K}rylov method exploiting negative curvature directions, for large scale unconstrained optimization},
	author={Fasano, Giovanni and Lucidi, Stefano},
	journal={Optimization Research Letters},
	volume={3},
	number={4},
	pages={521--535},
	year={2009}
}

@article{GF09a-short,
	title={A nonmonotone truncated {N}ewton--{K}rylov method exploiting negative curvature directions, for large scale unconstrained optimization},
	author={Fasano, Giovanni and Lucidi, Stefano},
        journal = 	 {Oper. Res. Lett.},	
	volume={3},
	pages={521--535},
	year={2009}
}

@inproceedings{KF04a,
author = {Fatahalian, K. and Sugerman, J. and Hanrahan, P.},
title = {Understanding the efficiency of GPU algorithms for matrix-matrix multiplication},
year = {2004},
booktitle = {Proceedings of the ACM SIGGRAPH/EUROGRAPHICS Conference on Graphics Hardware},
pages = {133--137}
}

@InProceedings{LAF01a,
  author = 	 {Lee A. Feldkamp and Timothy M. Feldkamp and Danil V. Prokhorov},
  title = 	 {An approach to adaptive classification},
  booktitle = 	 {Intelligent signal processing},
  editor    =    {Simon Haykin and Bart Kosko},
  publisher = 	 {IEEE Press},
  year =	 {2001}
}

@article{ERF19a,
  title={Evolutionary inversion of class distribution in overlapping areas for multi-class imbalanced learning},
  author = {Everlandio R.Q. Fernandes and Andre C.P.L.F. {de Carvalho}},
  journal={Information Sciences},
  volume={494},
  pages={141--154},
  year={2019}
}

@article{AF08a,
  title={A study of the behaviour of linguistic fuzzy rule based classification systems in the framework of imbalanced data-sets},
  author={Fern{\'a}ndez, Alberto and Garc{\'\i}a, Salvador and del Jesus, Mar{\'\i}a Jos{\'e} and Herrera, Francisco},
  journal={Fuzzy Sets and Systems},
  volume={159},
  number={18},
  pages={2378--2398},
  year={2008}
}

@article{MF14a,
  author  = {Manuel Fern\'{a}ndez-Delgado and Eva Cernadas and Sen\'{e}n Barro and Dinani Amorim},
  title   = {Do we Need Hundreds of Classifiers to Solve Real World Classification Problems?},
  journal = {Journal of Machine Learning Research},
  year    = {2014},
  volume  = {15},
  pages   = {3133-3181}
}

@article{MF14a-short,
  author  = {Manuel Fern\'{a}ndez-Delgado and Eva Cernadas and Sen\'{e}n Barro and Dinani Amorim},
  title   = {Do we Need Hundreds of Classifiers to Solve Real World Classification Problems?},
  journal = {JMLR},
  year    = {2014},
  volume  = {15},
  pages   = {3133--3181}
}


@article{MF03a,
author      = {Michael Ferris and Todd Munson},
journal     = {SIAM Journal on Optimization},
pages       = {783--804},
title       = {Interior point methods for massive support vector machines},
volume      = {13},
number      = {3},
year        = {2003}
}

@incollection{MF15a,
title = {Efficient and Robust Automated Machine Learning},
author = {Feurer, Matthias and Klein, Aaron and Eggensperger, Katharina and Springenberg, Jost and Blum, Manuel and Hutter, Frank},
booktitle = {Advances in Neural Information Processing Systems 28},
editor = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
pages = {2962--2970},
year = {2015}
}


@Article{SF01,
  author =       {Shai Fine and Katya Scheinberg},
  title =        {Efficient {SVM} Training Using Low-Rank Kernel Representations},
  journal =      {Journal of Machine Learning Research},
  volume =       {2},
  year =         {2001},
  pages =        {243--264}
}

@Article{SF01-short,
  author =       {Shai Fine and Katya Scheinberg},
  title =        {Efficient {SVM} Training Using Low-Rank Kernel Representations},
  journal =      {JMLR},
  volume =       {2},
  year =         {2001},
  pages =        {243--264}
}

@incollection{SF02a,
	title={Incremental learning and selective sampling via parametric optimization framework for {SVM}},
    author={Fine, Shai and Scheinberg, Katya},
 	booktitle={Advances in neural information processing systems},
	pages={705--712},
	year={2001},
	publisher={MIT}
}

@incollection{SF02a-short,
	title={Incremental learning and selective sampling via parametric optimization framework for {SVM}},
    author={Fine, Shai and Scheinberg, Katya},
	booktitle={NIPS},
	year={2001},
}

@Article{GWF01a,
  author = 	 {Gary William Flake and
Steve Lawrence},
  title = 	 {Efficient {SVM} regression training with {SMO}},
  year = 	 {2002},
journal={Machine Learning},
pages = {271--290},
volume = {46}
}


@Book{AVF83a,
  author =	 {A. V. Fiacco},
  title = 	 {Introduction to Sensitivity and Stability Analysis
in Nonlinear Programming},
  publisher = 	 {Academic Press},
  year = 	 {1983}
}

@article{RF64a,
	title={Function minimization by conjugate gradients},
	author={Fletcher, Reeves and Reeves, Colin M},
	journal={The Computer Journal},
	volume={7},
	number={2},
	pages={149--154},
	year={1964}
}

@article{RF70a,
    title={A new approach to variable metric algorithms},
    author={Fletcher, Roger},
    journal={The Computer Journal},
    volume={13},
    number={3},
    pages={317--322},
    year={1970}
}

@Book{RF87a,
  author = 	 "Roger Fletcher",
  title = 	 "Practical Methods of Optimization",
  publisher = 	 "John Wiley and Sons",
  year = 	 "1987"
}

@Article{RF05a,
  author = {Roger Fletcher},
  title = {On the {B}arzilai-{B}orwein Method},
  journal = {Optimization and Control with Applications},
  year = {2005},
  pages = {235--256},
  volume = {96}
}

@Article{LRF57a,
  author = 	 {Ford, Jr., L. R.},
  title = 	 {Solution of a Ranking Problem from Binary Comparisons},
  journal = 	 {American Mathematical Monthly},
  year = 	 {1957},
  OPTkey = 	 {},
  volume =	 {64},
  number =	 {8},
  pages =	 {28--33},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}



@Article{MF03b,
 author =       {M\'{a}rio A. T. Figueiredo},
 title =        {Adaptive Sparseness for Supervised Learning},
journal =      {IEEE Transactions on Pattern Analysis and Machine Intelligence},
 year =         {2003},
 volume =       {25},
 pages =        {1150--1159}
}

@Article{MF07a,
  author = {M\'{a}rio A. T. Figueiredo and Robert Nowak and
Stephen Wright},
  title = {Gradient Projection for Sparse
Reconstruction: Applications to Compressed Sensing
and Other Inverse Problems},
  journal = {IEEE Journal on Selected Topics in
Signal Processing},
  year = {2007},
  pages = {586--598},
  volume = {1}
}
%  url = {http://www.lx.it.pt/~mtf/GPSR},

@article{LF06a,
  title={{Nonnegative matrix factorization and I-divergence alternating minimization}},
  author={Finesso, L. and Spreij, P.},
  journal={Linear Algebra and Its Applications},
  volume={416},
  number={2--3},
  pages={270--287},
  year={2006},
  publisher={Elsevier}
}

@article{RAF36a,
author      = {Ronald A. Fisher},
journal     = {Annals of Eugenics},
pages       = {179--188},
title       = {The use of multiple measurements in taxonomic problem},
volume      = {7},
year        = {1936}
}

@ONLINE{FITBIT13a,
	author = {Fitbit},
	title = {Flex Wristband},
        howpublished = {\url{http://www.fitbit.com}}	
}


@article{PAF10a,
 title = {Consensus-Based Distributed Support Vector Machines},
 author = {Pedro Andr\'es Forero and Alfonso Cano and Georgios B. Giannakis},
 journal = {Journal of Machine Learning},
 volume = {11},
 pages = {1663--1707},
 year = {2010}
}


@article{AF95,
author      = "A. Forsgren and P. E. Gill and W. Murray",
title       = "Computing modified {N}ewton directions using a
               partial {C}holesky factorization",
journal     = "SIAM J. Sci. Comput.",
pages       = "139--150",
volume      = "16",
year        = "1995",
}

@article{AF97,
author      = {Anders Forsgren and Walter Murray},
title       = {Newton methods for large-scale linear
                  inequality-constrained  minimization},
journal     = {SIAM J. Optim.},
pages       = {162--176},
volume      = {7},
year        = {1997}
}


@Article{KF15a,
  author = 	 {Kimon Fountoulakis and Jacek Gondzio},
  title = 	 {A Second-Order Method for Strongly Convex $l1$-Regularization Problems},
  journal = 	 {Mathematical Programming},
  year = 	 {2015},
  OPTkey = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTpages = 	 {},
  OPTmonth = 	 {},
  note =	 {To appear},
  OPTannote = 	 {}
}

@Article{KF15a-short,
  author = 	 {Kimon Fountoulakis and Jacek Gondzio},
  title = 	 {A Second-Order Method for Strongly Convex $l1$-Regularization Problems},
  journal = 	 {Math. Program.},
  year = 	 {2015},
  note =	 {To appear}
}

@book {RF93a,
author      = {Robert Fourer and David M. Gay and Brian W. Kernighan},
title       = {{AMPL}: {A} Modeling Language for Mathematical Programming},
publisher   = {The Scientific Press},
year        = {1993},
}
		  
@inproceedings{VF08a,
 author = {Franc, Vojt\v{e}ch and Sonnenburg, Soeren},
 title = {Optimized Cutting Plane Algorithm for Support Vector Machines},
 booktitle = {Proceedings of the 25th International Conference on
Machine Learning},
 publisher = {ACM},
 year = {2008},
 pages = {320--327}
}

@inproceedings{VF11a,
author = {Franc, Vojt\v{e}ch and Zien, Alex and Sch\"{o}lkopf, Bernhard},
title = {Support vector machines as probabilistic models},
year = {2011},
booktitle = {Proceedings of the 28th International Conference on International Conference on Machine Learning (ICML)},
pages = {665--672}
}

@misc{AF10a,
author = "Andrew Frank and Arthur Asuncion",
year = "2010",
title = "{UCI} Machine Learning Repository",
url = "http://archive.ics.uci.edu/ml",
institution = "University of California, Irvine, School of Information and Computer Sciences" 
} 

@TechReport{RMF94a,
  author = 	 {R. M. Freund},
  title = 	 {Complexity of an algorithm for finding an approximate solution
of a semi-definite program with no regularity assumption},
  institution =  {Operations Research Center, Massachusetts Institute of
Technology},
  year = 	 {1994},
  number =	 {OR 302-94},
  address =	 {Cambridge, MA},
  note =         {Submitted to {\em Math.
   Programming}.}
}
% checked april 23

@TechReport{RWF97a,
  author = 	 {Roland W. Freund and Florian Jarre and Shinji Mizuno},
  title = 	 {Convergence of a class of inexact
     interior-point algorithms for linear programs        },
  institution =  {Bell Laboratories},
  year = 	 {1997},
  type = 	 {Numerical Analysis Manuscript 97--3--11},
  OPTaddress = 	 {Murray Hill, New Jersey}
}

@article{YF97a,
  title={A decision-theoretic generalization of on-line learning and an application 
to boosting},
  author={Yoav Freund and Robert E. Schapire},
  journal={Journal of Computer and System Sciences},
  volume={55},
  number={1},
  pages={119--139},
  year={1997}
}

@inproceedings{YF97b,
 author = {Freund, Yoav and Schapire, Robert E. and Singer, Yoram and
Warmuth, Manfred K.},
 title = {Using and combining predictors that specialize},
 booktitle = {Proceedings of the Twenty-ninth Annual ACM Symposium on
Theory of Computing},
 publisher = {ACM},
 year = {1997},
 pages = {334--343}
}

		  
@TechReport{JF88a,
  author = 	 {Jerome H. Friedman},
  title = 	 {Multivariate Adaptive Regression Splines},
  institution =  {Laboratory for Computational Statistics, Department of Statistics,
Stanford University},
  year = 	 {1988},
  number =	 {No. 102}
}


@TechReport{JF96a,
author = "Jerome H. Friedman",
    title = "Another approach to polychotomous classification",
    year = "1996",
  institution =  {Department of Statistics, Stanford University},
  url={http://www-stat.stanford.edu/~jhf/ftp/poly.pdf}
}

@article{JF01a,
 author={Friedman, Jerome H.},
 title={Greedy Function Approximation: A Gradient Boosting Machine},
 journal={Annals of Statistics},
 volume={29},
 number={5},
 pages={1189--1232},
 year={2001}
}

@article{JF07a,
  title={Pathwise coordinate optimization},
  author={Friedman, Jerome H. and Hastie, Trevor and H{\"o}fling, Holger and Tibshirani, Robert},
  journal={Annals of Applied Statistics},
  volume={1},
  number={2},
  pages={302--332},
  year={2007}
}

@Article{JF08a,
        author = {Friedman, Jerome H. and Hastie, Trevor and
Tibshirani, Robert},
        title = {Regularization paths for generalized linear models
via coordinate descent},
        journal = {Journal of Statistical Software},
        volume = {33},
        number = {1},
        pages = {1--22},
        year = {2010}
}

@Article{JF08a-short,
        author = {Friedman, Jerome H. and Hastie, Trevor and
Tibshirani, Robert},
        title = {Regularization paths for generalized linear models
via coordinate descent},
        journal = {JSS},
        volume = {33},
        pages = {1--22},
        year = {2010}
}

@InProceedings{TTF98a,
  author = 	 {T.-T. Friess and N. Cristianini and C. Campbell},
  title = 	 {The kernel
     adatron algorithm: a fast and
     simple learning procedure for
     support vector machines},
  booktitle = 	 {Proceedings of 15th
     {I}ntl. {C}onf. {M}achine {L}earning},
  year =	 {1998},
  publisher =	 {Morgan Kaufman Publishers}
}

@InProceedings{TTF98a-short,
  author = 	 {T.-T. Friess and N. Cristianini and C. Campbell},
  title = 	 {The kernel
     adatron algorithm: a fast and
     simple learning procedure for
     support vector machines},
  booktitle = 	 {ICML},
  year =	 {1998}
}


@inproceedings{JF09a,
author = {Froehlich, Jon and Dillahunt, Tawanna and Klasnja, Predrag and Mankoff, Jennifer and Consolvo, Sunny and Harrison, Beverly and Landay, James A.},
title = {UbiGreen: investigating a mobile tool for tracking and supporting green transportation habits},
booktitle = {Proceedings of the SIGCHI Conference on Human Factors in Computing Systems},
series = {CHI '09},
year = {2009},
isbn = {978-1-60558-246-7},
location = {Boston, MA, USA},
pages = {1043--1052},
numpages = {10},
url = {http://doi.acm.org/10.1145/1518701.1518861},
doi = {10.1145/1518701.1518861},
acmid = {1518861},
publisher = {ACM},
address = {New York, NY, USA},
keywords = {ambient displays, mobile phones, sensing, sustainability, transportation, ubicomp},
}

@Book{KSF82a,
  author = 	 "K. S. Fu",
  title = 	 "Syntatic Pattern Recognition with Applications",
  publisher = 	 "Prentics-Hall",
  year = 	 "1982",
  address =	 "Englewood Cliffs, NJ"
}

@Article{WJF98a,
  author = 	 {Wenjiang J. Fu},
  title = 	 {Penalized Regressions: The Bridge Versus the Lasso},
  journal = 	 {Journal of Computational and Graphical Statistics},

  year = 	 {1998},
  volume =	 {7},
  number = {3},
  pages =	 {397--416}
}


@TechReport{AF01a,
  author = 	 {A. Fuduli and M. Gaudioso and G. Giallomardo},
  title = 	 {Minimizing nonconvex nonsmooth functions via cutting
planes and proximity control},
  institution =  {Laboratorio di Logistica},
  year = 	 {2002}
}




@TechReport{KF95a,
  title = 	 {{SDPA} (Semidefinite Programming Algorithm) - User's
                  Manual}, 
  author = 	 {Katsuki Fujisawa and Masakazu Kojima and Kazuhide
                  Nakata},
  year = 	 {1995},
  institution =  {Tokyo Institute of Technology},
  month =	 {December},
  note =	 {Revised August 1996}
}


@Article{KF97a,
  author = 	 {Katsuki Fujisawa and Masakazu Kojima and Kazuhide Nakata},
  title = 	 {Exploiting Sparsity in Primal-Dual Interior-Point
                  Methods for Semidefinite Programming},
  journal = 	 {Math. Programming},
  year = 	 {1997},
  volume =	 {79},
  pages =	 {235--254}
}

@Misc{KF97b,
  author = 	 {Katsuki Fujisawa and Masakazu Kojima and Kazuhide Nakata},
  title =	 {Exploiting Sparsity in Primal-Dual Interior-Point
                  Methods for Semidefinite Programming},
  note =	 {Talk given at the 16th Mathematical Programming Symposium, Laussane},
  month =        {August 24-29},
  year =         {1997}
}

		  
		  
@Book{KF90a,
  author = 	 "K. Fukanaga",
  title = 	 "Introduction to Statistical Pattern Recognition",
  publisher = 	 "Academic Press",
  year = 	 "1990",
  address =	 "New York"
}


@article{GMF04a,
title={A feature selection {N}ewton method for support vector machine classification},
author={Fung, Glenn M. and Mangasarian, Olvi L.},
journal={Computational optimization and
applications},
volume={28},
pages={185--202},
year={2004}

}

@article{DG76a,
 title = {A dual algorithm for the solution of nonlinear variational problems via finite element approximation},
 author = {Daniel Gabay and Bertrand Mercier},
 journal = {Computers and Mathematics with Applications},
 volume = {2},
 issue = {1},
 pages = {17--40},
 year = {1976}
}

@InProceedings{EG04a,
  author       = {Edgar Gabriel and Graham E. Fagg and George Bosilca
                  and Thara Angskun and Jack J. Dongarra and Jeffrey
                  M. Squyres and Vishal Sahay and Prabhanjan Kambadur
                  and Brian Barrett and Andrew Lumsdaine and Ralph
                  H. Castain and David J. Daniel and Richard L. Graham
                  and Timothy S. Woodall},
  title        = {Open {MPI}: Goals, Concept, and Design of a Next
                  Generation {MPI} Implementation},
  booktitle    = {Proceedings of the 11th European PVM/MPI Users' Group
                  Meeting},
  year         = 2004,
  pages        = {97--104}
}

@InProceedings{EG04a-short,
  author       = {Edgar Gabriel and Graham E. Fagg and George Bosilca
                  and Thara Angskun and Jack J. Dongarra and Jeffrey
                  M. Squyres and Vishal Sahay and Prabhanjan Kambadur
                  and Brian Barrett and Andrew Lumsdaine and Ralph
                  H. Castain and David J. Daniel and Richard L. Graham
                  and Timothy S. Woodall},
  title        = {Open {MPI}: Goals, Concept, and Design of a Next
                  Generation {MPI} Implementation},
  booktitle    = {European PVM/MPI Users' Group Meeting},
  year         = 2004,
  pages        = {97--104}
}

@article{EMG84,
  author = {Eli M. Gafni and Dimitri P. Bertsekas},
  journal = {SIAM Journal on Control and Optimization},
  pages = {936--964},
  title = {Two-metric projection methods for constrained optimization},
  volume = {22},
  year = {1984}
}



@article{LG20a,
  author = 	 {Leonardo Galli and Chih-Jen Lin},
  journal={IEEE Transactions on Neural Networks and Learning Systems},
  title={A Study on Truncated {N}ewton Methods for Linear Classification},
  year={2022},
  volume={33},
  number={7},
  pages={2828--2841},
  url = {https://www.csie.ntu.edu.tw/~cjlin/papers/tncg/tncg.pdf},
  OPTkey = 	 {},
  OPTtype = 	 {},
  OPTnumber = 	 {},
  OPTaddress = 	 {},
  OPTmonth = 	 {},
  OPTannote = 	 {}
}

@article{LG20a-short,
  author = 	 {Leonardo Galli and Chih-Jen Lin},
  title = 	 {Truncated {N}ewton Methods for Linear Classification},
  journal = {IEEE TNNLS},
  volume={33},
  pages={2828--2841},
  year = 	 {2022}
}


@TechReport{LG20b,
  author = 	 {Leonardo Galli and Chih-Jen Lin},
  title = 	 {Release Note of LIBLINEAR 2.40},
  institution =  {National Taiwan University},
  year = 	 {2020},
  url = {https://www.csie.ntu.edu.tw/~cjlin/papers/tncg/release240.pdf},
  OPTkey = 	 {},
  OPTtype = 	 {},
  OPTnumber = 	 {},
  OPTaddress = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@Article{GG21a,
  author = 	 {Giulio Galvan  and Matteo Lapucci and Chih-Jen Lin and Marco Sciandrone},
  title = 	 {A Two-Level Decomposition Framework Exploiting First and Second Order Information for {SVM} Training Problems},
  journal = {Journal of Machine Learning Research},
  year = 	 {2021},
  volume  = {22},
  number  = {23},
  pages   = {1--38},
  url={https://www.csie.ntu.edu.tw/~cjlin/papers/19-632.pdf}
}

@inproceedings{ZG10a,
title={Learning attribute-to-feature mappings for cold-start recommendations},
author={Gantner, Zeno and Drumond, Lucas and Freudenthaler, Christoph and Rendle, Steffen and Schmidt-Thieme, Lars},
 booktitle = {Proceedings of the IEEE International Conference on Data Mining (ICDM)},
pages={176--185},
year={2010},
}

@inproceedings{ZG10a-short,
title={Learning attribute-to-feature mappings for cold-start recommendations},
author={Gantner, Zeno and Drumond, Lucas and Freudenthaler, Christoph and Rendle, Steffen and Schmidt-Thieme, Lars},
 booktitle = {ICDM},
year={2010}
}

@article{HG17b,
  title={Learning from class-imbalanced data: Review of methods and applications},
  author={Haixiang Guo and Yijing Li and Jennifer Shang and Mingyun Gu and Yuanyue Huang and Bing Gong},
  journal={Expert Systems With Applications},
  volume={73},
  pages={220--239},
  year={2017}
}

@inproceedings{HG17a,
title={Deep{FM}: a factorization-machine based neural network for CTR prediction},
author={Guo, Huifeng and Tang, Ruiming and Ye, Yunming and Li, Zhenguo and He, Xiuqiang},
booktitle={Proceedings of the 26th International Joint Conference on Artificial Intelligence (IJCAI)},
pages={1725--1731},
year={2017}
}

@inproceedings{HG17a-short,
title={Deep{FM}: a factorization-machine based neural network for CTR prediction},
author={Guo, Huifeng and Tang, Ruiming and Ye, Yunming and Li, Zhenguo and He, Xiuqiang},
booktitle={IJCAI},
year={2017}
}

@inproceedings{HG19a,
title={PAL: a position-bias aware learning framework for CTR prediction in live recommender systems},
author={Guo, Huifeng and Yu, Jinkai and Liu, Qing and Tang, Ruiming and Zhang, Yuzhou},
booktitle={Proceedings of the 13th ACM Conference on Recommender Systems},
pages={452--456},
year={2019}
}

@inproceedings{HG19a-short,
title={PAL: a position-bias aware learning framework for CTR prediction in live recommender systems},
author={Guo, Huifeng and Yu, Jinkai and Liu, Qing and Tang, Ruiming and Zhang, Yuzhou},
booktitle={RecSys},
year={2019}
}

@Article{JBG02a,
  author = 	 {J. B. Gao and S. R. Gunn and C. J. Harris and M. Brown},
  title = 	 {A probabilistic framework for {SVM} regression and error bar estimation},
  journal = 	 {Machine Learning},
  year = 	 {2002},
  volume =	 {46},
  pages =	 {71--89}
}

@InProceedings{JG07a,
  author =       {Jianfeng Gao and Galen Andrew and Mark Johnson and Kristina Toutanova},
  title =        {A Comparative Study of Parameter Estimation Methods Statistical Natural Language Processing},
  booktitle =    {Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics (ACL)},
  pages =        {824--831},
  year =         {2007}
}

@INPROCEEDINGS{JG06a,
  author={Gao, Jing and Tan, Pang-Ning},
  booktitle={Proceedings of the Sixth International Conference on Data Mining (ICDM)}, 
  title={Converting Output Scores from Outlier Detection Algorithms into Probability Estimates}, 
  year={2006},
  pages={212--221}
}

@INPROCEEDINGS{JG06a-short,
  author={Gao, Jing and Tan, Pang-Ning},
  booktitle={ICDM}, 
  title={Converting Output Scores from Outlier Detection Algorithms into Probability Estimates}, 
  year={2006}
}

@inproceedings{YG11a,
 author = {Gao, Yuan and Yang, Qingxuan and Li, Guanfeng and Chang, Edward Y. and Wang, Dong and Wang, Chengu and Qu, Hang and Dong, Pei and Zhang, Faen},
 title = {{XINS}: the anatomy of an indoor positioning and navigation architecture},
 booktitle = {Proceedings of the 1st international workshop on Mobile location-based service},
series = {MLBS '11},
year = {2011},
isbn = {978-1-4503-0928-8},
location = {Beijing, China},
pages = {41--50},
numpages = {10},
url = {http://doi.acm.org/10.1145/2025876.2025884},
doi = {10.1145/2025876.2025884},
acmid = {2025884},
publisher = {ACM},
address = {New York, NY, USA},
keywords = {calibration, inertial tracking, location, particle filters}
}


@Article{JLG03a,
  author =       {Jennifer L. Gardy and Cory Spencer and Ke Wang and Martin Ester and Gabor E. 
  Tusnady and Istvan Simon and Sujun Hua and Katalin deFays and Christophe Lambert and 
  Kenta Nakai and Fiona S.L. Brinkman},
  title =        {{PSORT-B}: improving protein 
  subcellular localization prediction for Gram-negative bacteria},
  journal =      {Nucleic Acids Research},
  year =         {2003},
  volume =       {31},
  number =       {13},
  pages =        {3613--3617}
}

@article{MG03a,
title={Building decision trees with constraints},
author={Garofalakis, Minos and Hyun, Dongjoon and Rastogi, Rajeev and Shim, Kyuseok},
journal={Data Mining and Knowledge Discovery},
volume={7},
number={2},
pages={187--214},
year={2003}
}

@Article{PHG94a,
  author = 	 {Paul H. Garthwaite},
  title = 	 {An interpretation of partial least
squares},
  journal = 	 {Journal of American Statistics Association},
  year = 	 {1994},
  volume =	 {89},
  number =	 {425},
  pages =	 {122--127}
}

@inproceedings{DMG84,
author      = {D. M. Gay},
booktitle   = {Numerical Analysis},
editor      = {D. F. Griffiths},
pages       = {72--105},
publisher   = {Springer-Verlag},
series      = {Lecture Notes in Mathematics 1066},
title       = {A trust region approach to linearly constrained optimization},
year        = {1984}
}

@TechReport{XG99a,
  title = 	 {Sequential Minimal Optimization},
  author =	 {Xianping Ge},
  year = {1999},
  note =	 {Software available at {\tt http://www.ics.uci.edu/\verb"~"xge/svm/}}
}

@article{ge:st,
author      = {S. Geman and D. Geman},
title       = {Stochastic Relaxation, Gibbs Distributions, and the Bayesian 
               Restoration of Images},
journal     = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
pages       = {721--741},
volume      = {6},
year        = {1984},
}

@inproceedings{RG11a,
 author = {Gemulla, Rainer and Nijkamp, Erik and Haas, Peter J. and Sismanis, Yannis},
 title = {Large-scale matrix factorization with distributed stochastic gradient descent},
 booktitle = {Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining},
 year = {2011},
 pages = {69--77}
} 

@inproceedings{RG11a-short,
 author = {Gemulla, Rainer and Nijkamp, Erik and Haas, Peter J. and Sismanis, Yannis},
 title = {Large-scale matrix factorization with distributed stochastic gradient descent},
 booktitle = {KDD},
 year = {2011},
 pages = {69--77},
 numpages = {9},
} 

@TechReport{RG11b,
  AUTHOR = {Gemulla, Rainer and Haas, Peter J. and Nijkamp, Erik and Sismanis, Yannis},
  TITLE = {Large-scale matrix factorization with distributed stochastic gradient descent},
  YEAR = {2011},
  TYPE = {Technical Report},
  INSTITUTION = {IBM Almaden Research Center},
  NUMBER = {RJ10481},
  PAGES = {47},
  ADDRESS = {San Jose, CA},
  MONTH = {March},
}

@article{AG06a,
         title={Large-scale {B}ayesian logistic regression for text 
categorization},
         author={Genkin, Alexandar and Lewis, David D. and Madigan, David},
         journal={Technometrics},
         year={2007},
         volume={49},
         number={3},
         pages={291--304},
}

@inproceedings{AG22a,
  author    = {Gera, Ariel and
               Halfon, Alon and
               Shnarch, Eyal and
               Perlitz, Yotam and
               Ein-Dor, Liat and
               Slonim, Noam},
  title     = {Zero-Shot Text Classification with Self-Training},
  booktitle = {Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP)},
  year      = {2022}
}

@techreport{EMG05a,
author      = {E. Michael Gertz and Joshua D. Griffin},
institution = {Argonne National Laboratory},
number      = {ANL/MCS-TM-289},
title       = {Support vector machine classifiers for large data sets},
year        = {2005}
}

@techreport{EG14a,
	title={Global convergence of the Heavy-ball method for convex
		optimization},
	author={Ghadimi, Euhanna and Feyzmahdavian, Hamid Reza and
		Johansson, Mikael},
	year={2014},
	note={arXiv preprint arXiv:1412.7457}
}

        
@InProceedings{NG05a-short,
  author = 	 {N. Ghamrawi and A. McCallum},
  title = 	 {Collective Multi-Label Classification},
  booktitle = 	 {CIKM},
  OPTcrossref =  {},
  OPTkey = 	 {},
  OPTpages = 	 {},
  year =	 {2005},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTaddress = 	 {},
  OPTmonth = 	 {},
  OPTorganization = {},
  OPTpublisher = {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@article{JG12a,
	author = {Giesen, Joachim and Jaggi, Martin and Laue, S\"{o}ren},
	title = {Approximating Parameterized Convex Optimization Problems},
	journal = {ACM Transactions on Algorithms},
	volume = {9},
	number = {1},
	year = {2012},
	pages = {10:1--10:17}
}

@article{JG12a-short,
	author = {J. Giesen and M. Jaggi and S. Laue},
	title = {Approximating Parameterized Convex Optimization Problems},
	journal = {TALG},
	volume = {9},
	year = {2012},
	pages = {10:1--10:17}
}

@article{PEG92a,
author      = {P. E. Gill and W. Murray and D. B. Poncel\'{e}on and
               M. A. Saunders},
title       = {Preconditioners for indefinite systems arising in optimization},
journal     = {SIAM J. Matrix Anal. Appl.},
pages       = {292--311},
volume      = {13},
year        = {1992},
}


@TechReport{PEG97a,
  author = 	 {P. E. Gill and W. Murray and M. A. Saunders},
  title = 	 {SNOPT: An SQP algorithm for large-scale
     constrained optimization},
  institution =  {Dept of
     EESOR, Stanford University},
  year = 	 {1997},
  number =	 {SOL 97-3}
}


@book{PEG81,
author      = {P. E. Gill and W. Murray and M. H. Wright},
publisher   = {Academic Press},
title       = {Practical Optimization},
year        = {1981}
}

@article{PCG62a,
author = "Gilmore, P.C.",
title = "Optimal and suboptimal algorithms for the quadratic assignment                  problem",
journal = "SIAM J. Appl. Math.",
volume = "10",
pages = "305--313",
year = "1962"
}

@inproceedings{AG18a,
title={Offline {A/B} testing for recommender systems},
author={Gilotte, Alexandre and Calauz{\`e}nes, Cl{\'e}ment and Nedelec, Thomas and Abraham, Alexandre and Doll{\'e}, Simon},
booktitle={Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining},
pages={198--206},
year={2018}
}

@inproceedings{AG18a-short,
title={Offline {A/B} testing for recommender systems},
author={Gilotte, Alexandre and Calauz{\`e}nes, Cl{\'e}ment and Nedelec, Thomas and Abraham, Alexandre and Doll{\'e}, Simon},
booktitle={WSDM},
year={2018}
}

@inproceedings{AG99a,
  author    = {A. Gionis and
               P. Indyk and
               R. Motwani},
  title     = {Similarity Search in High Dimensions via Hashing},
  booktitle = {Proceedings of VLDB},
  year      = {1999},
  pages     = {518-529}
}


@Book{IVG72a,
  author =	 {I. V. Girsanov},
  title = 	 {Lectures on Mathematical Theory of Extremum Problems},
  publisher = 	 {Springer-Verlag},
  year = 	 {1972},
  volume =	 {67},
  series =	 {Lecture Notes in Economics and Mathematical Systems},
  address =	 {Berlin}
}

@ARTICLE{TG06a,
  TITLE = {Maximum-Gain Working Set Selection for Support Vector Machines},
  AUTHOR = {Tobias Glasmachers and Christian Igel},
  JOURNAL = {Journal of Machine Learning Research},
  VOLUME = {7},
  PAGES = {1437-1466},
  YEAR = {2006}
}

@ARTICLE{TG06a-short,
  TITLE = {Maximum-Gain Working Set Selection for Support Vector Machines},
  AUTHOR = {Tobias Glasmachers and Christian Igel},
  JOURNAL = {JMLR},
  VOLUME = {7},
  PAGES = {1437-1466},
  YEAR = {2006}
}

@InProceedings{TG13a,
  title = 	 {Accelerated Coordinate Descent with Adaptive Coordinate Frequencies},
  author = 	 {Tobias Glasmachers and Urun Dogan},
  booktitle = 	 {Proceedings of the 5th Asian Conference on Machine Learning},
  pages = 	 {72--86},
  year = 	 {2013},
  volume = 	 {29},
  series = 	 {Proceedings of Machine Learning Research}
}

@InProceedings{TG13a-short,
  title = 	 {Accelerated Coordinate Descent with Adaptive Coordinate Frequencies},
  author = 	 {Tobias Glasmachers and Urun Dogan},
  booktitle = 	 {ACML},
  year = 	 {2013}
}

@inproceedings{AG12a,
  author = {Glazer, Assaf and Lindenbaum, Michael and Markovitch, Shaul},
  booktitle = {Advances in Neural Information Processing Systems},
  title = {Learning High-Density Regions for a Generalized {K}olmogorov-{S}mirnov Test in High-Dimensional Data},
  volume = {25},
  year = {2012}
}

@article{AG13a,
  title={q-{OCSVM}: A q-quantile estimator for high-dimensional distributions},
  author={Glazer, Assaf and Lindenbaum, Michael and Markovitch, Shaul},
  journal={Advances in Neural Information Processing Systems},
  volume={26},
  year={2013}
}

@PhdThesis{MEG93a,
  author = 	 {Glickman, Mark E.},
  title = 	 {Paired comparison models with time-varying
    parameters},
  school = 	 {Department of Statistics, Harvard
    University},
  year = 	 {1993},
  OPTkey = 	 {},
  OPTtype = 	 {},
  OPTaddress = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@article{MEG95a,
  author={Glickman, Mark E.},
  title={Chess rating systems},
  journal={American Chess Journal},
  volume={3},
  pages={59--102},
  year={1995}
}

@Article{MEG99a,
  author = 	 {Mark E. Glickman},
  title = 	 {Parameter estimation in large dynamic paired comparison experiments},
  journal = 	 {Applied Statistics},
  year = 	 {1999},
  volume =	 {48},
  pages =	 {377--394}
}

@inproceedings{XG10a,
  title={Understanding the difficulty of training deep feedforward
neural networks},
  author={Glorot, Xavier and Bengio, Yoshua},
  booktitle = {Proceedings of the 13th International Conference on Artificial Intelligence and Statistics (AISTATS)},
  pages={249--256},
  year={2010}
}

@article{KG96,
author      = {K. Goebel},
journal     = {Sun Developer News},
title       = {Getting more out of your new {UltraSPARC$^{\mbox{TM}}$} Machine},
volume      = {1},
year        = {1996}
}



@article{MG95,
author     = {M. X. Goemans and D. P. Williamson},
journal    = {J. Assoc. Comput. Mach.},
pages      = {1115--1145},
title      = {Improved approximation algorithms for maximum cut and 
	      satisfiability problems using semidefinite programming}, 
volume     = {42},
year       = {1995}
}

@inproceedings{KSG01a,
 author = {Goh, King-Shy and Chang, Edward and Cheng, Kwang-Ting},
 title = {SVM Binary Classifier Ensembles for Image Classification},
 booktitle = {Proceedings of the Tenth International Conference on Information and Knowledge Management (CIKM)},
 year = {2001},
 pages = {395--402}
}

@article{DG91a,
 author = {David Goldberg},
 title = {What every computer scientist should know about floating-point arithmetic},
 journal = {ACM Computing Surveys},
 volume = {23},
 number = {1},
 year = {1991},
 pages = {5--48}
 }

@InProceedings{YG08a,
    author={Goldberg, Yoav and Elhadad, Michael},
    title={split{SVM}: Fast, Space-Efficient, non-Heuristic, Polynomial
Kernel Computation for {NLP} Applications},
    booktitle={Proceedings of the 46st Annual Meeting of the  
Association of Computational Linguistics (ACL)},
    year={2008}
}

@InProceedings{YG08a-short,
   author={Goldberg, Yoav and Elhadad, Michael},
   title={split{SVM}: Fast, Space-Efficient, non-Heuristic, Polynomial  
Kernel Computation for {NLP} Applications},
   booktitle={Proceedings of ACL},
   year={2008}
}

@article{DG70a,
    title={A family of variable-metric methods derived by
        variational means},
    author={Goldfarb, Donald},
    journal={Mathematics of Computation},
    volume={24},
    number={109},
    pages={23--26},
    year={1970}
}

@book{GHG89,
author      = {G. H. Golub and Van Loan, C. F.},
title       = {Matrix Computations},
publisher   = {The Johns Hopkins University Press},
edition     = {Second},
year        = {1989}
}

@book{GHG96a,
author      = {G. H. Golub and Van Loan, C. F.},
title       = {Matrix Computations},
publisher   = {The Johns Hopkins University Press},
edition     = {Third},
year        = {1996}
}

@book{GHG12a,
author      = {Gene H. Golub and Van Loan, Charles. F.},
title       = {Matrix Computations},
publisher   = {The Johns Hopkins University Press},
edition     = {Fourth},
year        = {2012}
}

@article{TG99a,
  author={Golub, T. R. and Slonim, D. K. and Tamayo, P. and Huard, C. and Gaasenbeek, M. and Mesirov, J. P. and Coller, H. and Loh, M. L. and Downing, J. R. and Caligiuri, M. A. and C. D. Bloomfield and E. S. Lander},
  title={Molecular classification of cancer: class discovery and class prediction by gene expression monitoring},
  journal={Science},
  volume={286},
  number={5439},
  pages={531},
  year={1999}
}

@inproceedings{CG21a,
  author    = {Christian Gomes and
               Marcos Andr{\'{e}} Gon{\c{c}}alves and
               Leonardo Rocha and
               S{\'{e}}rgio D. Canuto},
  title     = {On the Cost-Effectiveness of Stacking of Neural and Non-Neural Methods
               for Text Classification: Scenarios and Performance Prediction},
  booktitle = {Findings of the Association for Computational Linguistics: {ACL/IJCNLP}},
  pages     = {4003--4014},
  year      = {2021},
  doi       = {10.18653/v1/2021.findings-acl.350}
}

@inproceedings{CG21a-short,
  author    = {Christian Gomes and
               Marcos Andr{\'{e}} Gon{\c{c}}alves and
               Leonardo Rocha and
               S{\'{e}}rgio D. Canuto},
  title     = {On the Cost-Effectiveness of Stacking of Neural and Non-Neural Methods
               for Text Classification: Scenarios and Performance Prediction},
  booktitle = {ACL},
  year      = {2021}
}

@article{CAG16a,
  title={The netflix recommender system: Algorithms, business value, and innovation},
  author={Gomez-Uribe, Carlos A. and Hunt, Neil},
  journal={ACM Transactions on Management Information Systems (TMIS)},
  volume={6},
  number={4},
  pages = {13:1--13:19},  
  year={2016}
}

@article{CAG16a-short,
  title={The netflix recommender system: Algorithms, business value, and innovation},
  author={Gomez-Uribe, Carlos A. and Hunt, Neil},
  journal={ACM TMIS},
  volume={6},
  pages = {13:1--13:19},  
  year={2016}
}

@inproceedings{PG15b,
    title={A modified orthant-wise limited memory quasi-{N}ewton
        method with convergence analysis},
    author={Gong, Pinghua and Ye, Jieping},
  booktitle = {Proceedings of the 32nd International Conference on
               Machine Learning (ICML)},
    year={2015}
}

@inproceedings{PG15b-short,
    title={A modified orthant-wise limited memory quasi-{N}ewton
        method with convergence analysis},
    author={Gong, Pinghua and Ye, Jieping},
    booktitle = {ICML},
    year={2015}
}


@ARTICLE{YG10a,
  author = {Yue Gong  and Joseph E. Beck and Neil T. Heffernan},
  title = {Comparing Knowledge Tracing and Performance Factor Analysis by Using Multiple Model Fitting Procedures},
  journal = {Intelligent Tutoring Systems},
  year = {2010}
}

@TechReport{EFG05a,
  author = 	 {Edward F. Gonzales and Yin Zhang},
  title = 	 {Accelerating the {L}ee-{S}eung algorithm for non-negative matrix factorization},
  institution =  {Department of Computational and Applied Mathematics, Rice University},
  year = 	 {2005},
  OPTkey = 	 {},
  OPTtype = 	 {},
  OPTnumber = 	 {},
  OPTaddress = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@TechReport{EFG05a-short,
  author = 	 {Edward F. Gonzales and Yin Zhang},
  title = 	 {Accelerating the {L}ee-{S}eung algorithm for non-negative matrix factorization},
  institution =  {Rice University},
  year = 	 {2005},
}

@misc{IJG13a,
  title={Pylearn2: a machine learning research library},
  author={Goodfellow, Ian J. and Warde-Farley, David and Lamblin, Pascal and Dumoulin, Vincent and Mirza, Mehdi and Pascanu, Razvan and Bergstra, James and Bastien, Fr{\'e}d{\'e}ric and Bengio, Yoshua},
  note={arXiv:1308.4214},  
  year={2013}
}

@inproceedings{IJG13b,
  title = 	 {Maxout Networks},
  author = 	 {Goodfellow, Ian J. and Warde-Farley, David and Mirza, Mehdi and Courville, Aaron and Bengio, Yoshua},
  booktitle = 	 {Proceedings of the 30th International Conference on Machine Learning (ICML)},
  pages = 	 {1319--1327},
  year = 	 {2013}
}

@inproceedings{IJG13b-short,
  title = 	 {Maxout Networks},
  author = 	 {Goodfellow, Ian J. and Warde-Farley, David and Mirza, Mehdi and Courville, Aaron and Bengio, Yoshua},
  booktitle = 	 {ICML},
  year = 	 {2013}
}

@book{IJG16a,
 author = {Goodfellow, Ian J. and Bengio, Yoshua and Courville, Aaron},
 title = {Deep Learning},
 year = {2016},
 publisher = {The MIT Press}
} 


@inproceedings{JG02a,
  author    = {Joshua Goodman},
  title     = {Sequential Conditional Generalized Iterative Scaling},
  booktitle =    {Proceedings of the 40th Annual Meeting of the Association of Computational Linguistics (ACL)},
  year      = {2002},
  pages     = {9--16}
}


@inproceedings{JG02a-short,
  author    = {Joshua Goodman},
  title     = {Sequential Conditional Generalized Iterative Scaling},
  booktitle = {ACL},
  year      = {2002}
}


@inproceedings{JG04a,
  author = {Joshua Goodman},
  title = {Exponential Priors for Maximum Entropy Models},
  booktitle = {Proceedings of the Annual Meeting of the Association
for Computational Linguistics},
  year = {2004}
}

@ONLINE{GOOGLE13a,
	author = {Google},
	title = {Google Now},
	howpublished = {\url{http://www.google.com/landing/now/}}
}


@inproceedings{SG13a,
   Author = {Siddharth Gopal and Yiming Yang},
   Title = {Distributed training of Large-scale Logistic models},
   Booktitle = {Proceedings of the 30th International Conference on Machine Learning (ICML)},
   Year = {2013},
   Pages = {289-297}
  }

@inproceedings{PG15a,
	title={Scalable Recommendation with Hierarchical Poisson
		Factorization},
	author={Gopalan, Prem and Hofman, Jake M. and Blei, David M.},
	booktitle = {Proceedings of the Thirty-First Conference on
		Uncertainty in Artificial Intelligence (UAI)},
	year = {2015},
	pages = {326--335}
}

@inproceedings{PG15a-short,
        title={Scalable Recommendation with Hierarchical Poisson
                Factorization},
        author={Gopalan, Prem and Hofman, Jake M. and Blei, David M.},
        booktitle = {UAI},
        year = {2015},
        pages = {326--335}
}

@Article{SAG97a,
  author = 	 {Goreinov, S. A. and Tyrtyshnikov, E. E. and Yeremin, A. Yu.},
  title = 	 {Matrix-free iterative      
                   solution strategies for    
                   large dense linear         
                   systems},
  journal = 	 {Numer. Linear Algebra      
                   Appl.                      },
  year = 	 {1997},
  volume =	 {4},
  number =	 {4},
  pages =	 {273--294}
}

@Article{ICG06a,
author =       {Isobel C. Gormley and Thomas B. Murphy},
title =        {Analysis of {I}rish third-level college applications data},
journal =      {Journal of the Royal Statistical Society Series A},
year    =      {2006},
volume =       {169},
pages =        {361--379}
}

@inproceedings{RG19a,
title={{RSN}: Randomized Subspace {N}ewton},
author={Gower, Robert and Koralev, Dmitry and Lieder, Felix and Richt{\'a}rik, Peter},
year={2019},
booktitle={Advances in Neural Information Processing Systems},
pages={614--623}
}

@inproceedings{RG19a-short,
title={{RSN}: Randomized Subspace {N}ewton},
author={Gower, Robert and Koralev, Dmitry and Lieder, Felix and Richt{\'a}rik, Peter},
year={2019},
booktitle={NIPS}
}

@article{PG18a,
title = {Graph embedding techniques, applications, and performance: A survey},
author = {Palash Goyal and Emilio Ferrara},
journal = {Knowledge-Based Systems},
volume = {151},
pages = {78-94},
year = {2018}
}

@inproceedings{TG10a,
  author = {Graepel, Thore and Candela, Joaquin Quinonero and Borchert, Thomas and Herbrich, Ralf},
  booktitle = {Proceedings of the Twenty Seventh International Conference on Machine Learning (ICML)},
  pages = {13-20},
  title = {Web-Scale {B}ayesian Click-Through rate Prediction for Sponsored Search Advertising in {M}icrosoft's {B}ing Search Engine.},
  year = {2010}
}

@inproceedings{KG05a,
  author    = {Kristen Grauman and Trevor Darrell},
  title     = {The Pyramid Match Kernel: Discriminative Classification with Sets of Image Features},
  booktitle = {Proceedings of IEEE International Conference on Computer Vision},
  year      = {2005}
}
%  address   = {Beijing, China},
%  month     = {October},


@Article{AG93a,
  author = 	 {A. Greenbaum and L. Greengard and G. B. McFadden},
  title = 	 {Laplace's equation and the {D}irichlet-{N}eumann map in multiply connected domains},
  journal = 	 {J. Comp. Phys.},
  year = 	 {1993},
  volume =	 {105},
  number =	 {2},
  pages =	 {267--278}
}


@TechReport{AG01a,
  author =	 {A. Gretton and R. Herbrich and O.
                  Chapelle and B. Sch\"olkopf and P.
                  J. W. Rayner},
  title =	 {{Estimating the Leave-One-Out Error for
                  Classification Learning with SVMs}},
  institution =	 {Cambridge University Engineering Department},
  year =	 {2001},
  number = 	 {CUED/F-INFENG/TR.424}
}


@Book{AG02b,
  author = {Griewank, Andreas},
  title = {Evaluating derivatives: principles and techniques of
algorithmic differentiation},
  publisher = {SIAM},
  year = {2000}
}


@article{TG04a, 
title={Finding scientific topics}, 
volume={101}, 
journal={Proceedings of the National Academy of Sciences}, 
author={Griffiths, Thomas L and Steyvers, Mark}, 
year={2004}, 
pages={5228--5235}
}

@Article{LG86a,
  author = {Luigi Grippo and Francesco Lampariello and Stefano Lucidi},
  title = {A nonmonotone line search technique for {N}ewton's method},
  journal = {SIAM Journal on Numerical Analysis},
  year = {1986},
  pages = {707--716},
  volume = {23}
}

@Article{LG99a,
title = "Globally Convergent Block-coordinate Techniques for Unconstrained 
Optimization",
author="Luigi Grippo and Marco Sciandrone",
journal = "Optimization Methods and Software",
year = "1999",
volume = "10",
pages = "587--637",
  OPTkey = 	 {},
  OPTnumber = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@Article{LG99a-short,
title = "Globally Convergent Block-coordinate Techniques for
Unconstrained Optimization",
author="Grippo, L. and Sciandrone, M.",
journal = "Optim. Methods Softw.",
year = "1999",
volume = "10",
pages = "587--637",
  OPTkey =       {},
  OPTnumber =    {},
  OPTmonth =     {},
  OPTnote =      {},
  OPTannote =    {}
}

@Article{LG00a,
  author = 	 {L. Grippo and M. Sciandrone},
  title = 	 {On the convergence of the block nonlinear {G}auss-{S}eidel method under convex constraints},
  journal = 	 {Operations Research Letters},
  year = 	 {2000},
  OPTkey = 	 {},
  volume =	 {26},
  OPTnumber = 	 {},
  pages =	 {127--136},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@Article{LG00a-short,
  author = 	 {L. Grippo and M. Sciandrone},
  title = 	 {On the convergence of the block nonlinear {G}auss-{S}eidel method under convex constraints},
  journal = 	 {Oper. Res. Lett.},
  year = 	 {2000},
  volume =	 {26},
  pages =	 {127--136}
}


@Article{LG02a,
  author={Luigi Grippo and Marco Sciandrone},
  title = {Nonmonotone Globalization Techniques for
 the {B}arzilai-{B}orwein Gradient Method},
  journal = {Computational Optimization and Applications},
  year = {2002},
  pages = {143--169},
  volume = {23}
}


@book{IG09a,
  title={Linear and nonlinear optimization},
  author={Griva, Igor and Nash, Stephen G. and Sofer, Ariela},
  year={2009},
  edition = {Second},
  publisher={SIAM}
}

@InCollection{WG97a,
author      = {William Gropp and Jorge J. Mor\'e},
title       = {Optimization environments and the {NEOS} Server},
booktitle   = {Approximation Theory and Optimization},
publisher   = {Cambridge University Press},
year        = {1997},
editor      = {M. D. Buhmann and A. Iserles},
pages       = {167--182},
}

@book{WG99a,
  author        = "William Gropp and Ewing Lusk and Anthony Skjellum",
  editor        = "",
  title         = "Using MPI-2: Advanced Features of the Message-Passing Interface",
  series        = "",
  publisher     = "MIT Press,",
  address       = "",
  year          = "1999",
  volume        = "",
};

@inproceedings{RG16a,
  title={A kronecker-factored approximate fisher matrix for convolution layers},
  author={Grosse, Roger and Martens, James},
  booktitle={International Conference on Machine Learning},
  pages={573--582},
  year={2016}
}

@TechReport{AG02a,
  author = 	 {Andreas Grothey},
  title = 	 {A Second Order Trust Region Bundle Method for Nonconvex Nonsmooth Optimization
},
  institution =  {Department of Mathematics and Statistics, University of Edinburgh},
  year = 	 {2002},
  number =	 {MS-02-005}
}

@inproceedings{AG16a,
author = {Grover, Aditya and Leskovec, Jure},
title = {Node2vec: scalable feature learning for networks},
year = {2016},
doi = {10.1145/2939672.2939754},
booktitle = {Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)},
pages = {855–864}
}

@inproceedings{AG19a,
title={Offline Evaluation to Make Decisions About Playlist Recommendation Algorithms},
author={Gruson, Alois and Chandar, Praveen and Charbuillet, Christophe and McInerney, James and Hansen, Samantha and Tardieu, Damien and Carterette, Ben},
booktitle={Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining},
pages={420--428},
year={2019}
}

@inproceedings{AG19a-short,
title={Offline Evaluation to Make Decisions About Playlist Recommendation Algorithms},
author={Gruson, Alois and Chandar, Praveen and Charbuillet, Christophe and McInerney, James and Hansen, Samantha and Tardieu, Damien and Carterette, Ben},
booktitle={WSDM},
year={2019}
}

@inproceedings{FG20a,
 author = {Gu, Fangda and Chang, Heng and Zhu, Wenwu and Sojoudi, Somayeh and El Ghaoui, Laurent},
 booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
 pages = {11984--11995},
 title = {Implicit Graph Neural Networks},
 year = {2020}
}

@TechReport{MG97a,
  author = 	 {M. Gu},
  title = 	 {On primal-dual interior point methods for semidefinite programming},
  institution =  {Department of Mathematics, University of California},
  year = 	 {1997},
  type =	 {CAM report},
  number =	 {97--12},
  address =	 {Los Angeles, CA}
}

@inproceedings{QG13a,
  author = {Gu, Quanquan and Han, Jiawei},
  title = {Clustered Support Vector Machines},  
  booktitle = {Proceedings of the 16th International Conference on Artificial Intelligence and Statistics (AISTATS)},
  pages = {307--315},
  year = {2013}
}

@inproceedings{QG13a-short,
  author = {Gu, Quanquan and Han, Jiawei},
  title = {Clustered Support Vector Machines},  
  booktitle = {AISTATS},
  year = 2013
}

@TechReport{YG00a,
  author = 	 {Yann Guermeur                   },
  title = 	 {Combining Discriminant Models   
                    with New Multiclass SVMs        },
  institution =  {LORIA Campus Scientifique       },
  year = 	 {2000},
  type =	 {Neuro COLT
     Technical Report},
  number =	 {NC-TR-00-086 },
}

@inproceedings{RG15a,
  title={User modeling for a personal assistant},
  author={Guha, Ramanathan and Gupta, Vineet and Raghunathan, Vivek and Srikant, Ramakrishnan},
  booktitle={Proceedings of the Eighth ACM International Conference on Web Search and Data Mining},
  pages={275--284},
  year={2015}
}

@inproceedings{RG15a-short,
  title={User modeling for a personal assistant},
  author={Guha, Ramanathan and Gupta, Vineet and Raghunathan, Vivek and Srikant, Ramakrishnan},
  booktitle={WSDM},
  year={2015}
}

@inproceedings{JG09a,
   author    = {John Guiver and Edward Snelson},
   title     = {Bayesian inference for {P}lackett-{L}uce ranking model},
   booktitle = {Proceedings of the Twenty Sixth International Conference
on Machine Learning (ICML)},
   year      = {2009},
   pages     = {},
}

@inproceedings{AG08a,
  title = {Tied {B}oltzmann machines for cold start recommendations},
  author = {Gunawardana, Asela and Meek, Christopher},
  booktitle = {Proceedings of the 2008 ACM conference on Recommender systems},
  pages = {19--26},
  year = {2008}
}

@inproceedings{AG08a-short,
  title = {Tied {B}oltzmann machines for cold start recommendations},
  author = {Gunawardana, Asela and Meek, Christopher},
  booktitle = {RecSys},
  year = {2008}
}

@inproceedings{AG09a,
  title = {A Unified Approach to Building Hybrid Recommender Systems},
  author = {Gunawardana, Asela and Meek, Christopher},
  booktitle = {Proceedings of the third ACM Conference on Recommender Systems},
  pages = {117--124},
  year = {2009}
}

@inproceedings{AG09a-short,
  title = {A Unified Approach to Building Hybrid Recommender Systems},
  author = {Gunawardana, Asela and Meek, Christopher},
  booktitle = {RecSys},
  year = {2009}
}

@inproceedings{QG16a,
  title = {Large-scale analysis of viewing behavior: Towards measuring satisfaction with mobile proactive systems},
  author = {Guo, Qi and Song, Yang},
  booktitle = {Proceedings of the 25th ACM International on Conference on Information and Knowledge Management (CIKM)},
  pages = {579--588},
  year = {2016}
}

@inproceedings{QG16a-short,
  title = {Large-scale analysis of viewing behavior: Towards measuring satisfaction with mobile proactive systems},
  author = {Guo, Qi and Song, Yang},
  booktitle = {CIKM},
  year = {2016}
}

@article{IG78,
author      = {I. Gustafsson},
journal     = {BIT},
pages       = {142--156},
title       = {A class of first order factorization methods},
volume      = {18},
year        = {1978}
}

@inproceedings{IG83,
author      = {I. Gustafsson},
booktitle   = {Preconditioning Methods: Theory and Applications},
editor      = {D. Evans},
pages       = {265--293},
publisher   = {Gordon and Breach},
title       = {Modified incomplete {C}holesky {(MIC)} methods},
year        = {1983}
}

@inproceedings{IG90,
author      = {I. Gustafsson},
booktitle   = {Preconditioning Conjugate Gradient Methods},
editor      = {O. Axelsson and Koltilina, L. Yu.},
publisher   = {Springer-Verlag},
title       = {A class of preconditioned conjugate gradient methods
               applied to the finite element equations},
pages       = {44--57},
year        = {1990}
}

@inproceedings{LJG78a,
  author={Guibas, Leo J. and Sedgewick, Robert},
  title={A dichromatic framework for balanced trees},
  booktitle={Proceedings of the 19th Annual Symposium on Foundations of Computer Science (FOCS)},
  pages={8--21},
  year={1978},
  organization={IEEE}
}

@article{SG19a,
      title={Network Representation Learning: Consolidation and Renewed Bearing}, 
      author={Saket Gurukar and Priyesh Vijayan and Aakash Srinivasan and Goonmeet Bajaj and Chen Cai and Moniba Keymanesh and Saravana Kumar and Pranav Maneriker and Anasua Mitra and Vedang Patel and Balaraman Ravindran and Srinivasan Parthasarathy},
      year={2019},
      journal={arXiv preprint arXiv:1905.00987}
}

@TechReport{IG97a,
  title={A scaling law for the validation-set training-set size ratio},
  author={Guyon, Isabelle},
  institution =  {AT\&T Bell Laboratories},
  year = 	 {1997},
  OPTkey = 	 {},
  OPTtype = 	 {},
  OPTnumber = 	 {},
  OPTaddress = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}



@Article{IG00a,
  author = {Isabelle Guyon and Jason Weston and Stephen Barnhill and  
Vladimir Vapnik},
  title = 	 {Gene Selection for Cancer
          Classification using Support Vector
          Machines},
  year = 	 {2002},
  journal =	 {Machine
          Learning},
  volume={46},
  pages={389--422}
}

@article{IG03a,
author = {Isabelle Guyon and Andre Elisseeff},
title = {An introduction to variable and feature selection},
  journal = {Journal of Machine Learning Research},
volume = {3},
year = {2003},
issn = {1533-7928},
pages = {1157--1182},
publisher = {MIT Press},
address = {Cambridge, MA, USA},
}

@incollection{IG05a,
  title = {Result Analysis of the {NIPS} 2003 Feature Selection Challenge},
  author = {Isabelle Guyon and Steve Gunn and Asa Ben Hur and Gideon Dror},
  booktitle = {Advances in Neural Information Processing Systems},
  volume = {17},
  year = {2005}
}

@InProceedings{IG05a-short,
  title = {Result Analysis of the {NIPS} 2003 Feature Selection Challenge},
  author = {Isabelle Guyon and Steve Gunn and Asa Ben Hur and Gideon Dror},
  booktitle = {NIPS},
  year = {2005}
}


@InProceedings{IG08a,
  author = {Isabelle Guyon and Constantin Aliferis and Greg Cooper and  
Andr\'e Elisseeff and Jean-Philippe Pellet and Peter Spirtes and  
Alexander Statnikov},
  title = {Design and Analysis of the Causation and Prediction Challenge},
  booktitle = {JMLR: Workshop and Conference Proceedings},
  year = {2008}
}

@InProceedings{IG10a,
 author = {Isabelle Guyon and Gavin Cawley and Gideon Dror and Vincent Lemaire},
 title = {Results of the Active Learning Challenge},
 booktitle = {JMLR Workshop and Conference Proceedings: Workshop on Active Learning and Experimental Design},
 year = {2010}
}


  @InProceedings{BH02a,
author = "B. Haasdonk and D. Keysers",
  title = "Tangent Distance Kernels for Support Vector Machines",
  booktitle =    {Proceedings of the 16th ICPR},
  pages =        {864--868},
  year =         {2002}
}

@book {WH94,
author      = {Wolfgang Hackbusch},
title       = {Iterative Solution of Large Sparse Systems of Equations},
publisher   = {Springer-Verlag},
year        = {1994},
series      = {Applied Mathematical Sciences 95}
}


@article{SWH89a,
	 author = "Hadley, S.W. and Rendl, F. and Wolkowicz, H.",
	 title = "A new lower bound via projection for the quadratic
		  assignment problem",
	 journal= "Math. Oper. Res.",
	 volume = 17,
	 number = 3,
	 pages = "727--739",
	 year = "1992"
         }




@Book{LH81a,
  author = 	 {L. Hageman and D. Young},
  title = 	 {Applied Iterative Methods},
  publisher = 	 {Academic Press},
  year = 	 {1981},
  address =	 {New York}
}

@article{WWH06a,
	title={A survey of nonlinear conjugate gradient methods},
	author={Hager, William W and Zhang, Hongchao},
	journal={Pacific Journal of Optimization},
	volume={2},
	number={1},
	pages={35--58},
	year={2006}
}

@inproceedings{ha:tu,
author      = {B. Hajek},
booktitle   = {24th IEEE Conf. Decision Contr.},
pages       = {755--760},
title       = {A tutorial survey of theory and applications of
               simulated annealing},
year        = {1985}
}

@Article{ETH08a,
  author = {Elaine T. Hale and Wotao Yin and Yin Zhang}, 
  title = {Fixed-Point Continuation for l1-Minimization: Methodology and Convergence},
  journal = {SIAM Journal on Optimization},
  year = {2008},
  volume = {19},
  number = {3},
  pages = {1107--1130}
}

@inproceedings{KBH10a,
	title = {Map{R}educe/{B}igtable for Distributed Optimization},
	author  = {Keith B. Hall and Scott Gilpin and Gideon Mann},
	year  = 2010,
	booktitle = {Neural Information Processing Systems Workshop on Leaning on Cores, Clusters, and Clouds}
}

@inproceedings{KBH10a-short,
	title = {Map{R}educe/{B}igtable for Distributed Optimization},
	author  = {Keith B. Hall and Scott Gilpin and Gideon Mann},
	year  = 2010,
	booktitle = {NIPS Workshop on LCCC}
}

@ARTICLE{MH09a,  
	author = {Mark Hall and Eibe Frank and Geoffrey Holmes 
		and Bernhard Pfahringer and Peter Reutemann and Ian H. Witten}, 
	title = {The {WEKA} data mining software: an update},  
	journal = {SIGKDD Explorations},  
	volume = {11},  
	issue = {1},  
	year = {2009}
}

@article{MH09a-short,
	author = {Mark Hall and Eibe Frank and Geoffrey Holmes 
		and Bernhard Pfahringer and Peter Reutemann and Ian H. Witten}, 
	title = {The {WEKA} data mining software: an update},
	journal = {SIGKDD Explor. Newsl.},
	year = {2009},
	publisher = {ACM}
} 

@article{AH09a,
  author = {Alon Halevy and Peter Norvig and Fernando Pereira},
  journal = {IEEE Intelligent Systems},
  number = 2,
  pages = {8-12},
  title = {The Unreasonable Effectiveness of Data},
  volume = 24,
  year = 2009
}

@InProceedings{RH13a,
    author = {Raffay Hamid and Dennis Decoste and Chih-Jen Lin},
    title = {Dense Non-rigid Point-Matching Using Random Projections},
    booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
    year = {2013}
}

@inproceedings{WLH17a,
 author = {Hamilton, Will and Ying, Zhitao and Leskovec, Jure},
 booktitle = {Advances in Neural Information Processing Systems},
 title = {Inductive representation learning on large graphs},
 year = {2017}
}

@inproceedings{EHH00a,
	author = {Eui-Hong Han and George Karypis},
	title = {Centroid-Based Document Classification: Analysis and Experimental Results},
	booktitle = {Proceedings of the 4th European Conference on Principles of Data Mining and Knowledge Discovery},
	year = {2000},
	pages = {424--431},
	numpages = {8}
}



@Book{JH11a,
  author =	 {Jiawei Han and Micheline Kamber and Jian Pei},
  title = 	 {Data Mining: Concepts and Techniques},
  publisher = 	 {Morgan Kaufmann},
  year = 	 {2011},
  OPTkey = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTaddress = 	 {},
  edition =	 {Third},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@article{LH09a,
  title={Alternating projected {B}arzilai-{B}orwein Methods For Nonnegative Matrix Factorization},
  author={Han, Lixing and Neumann, Michael and Prasad, Upendra},
  journal = 	 {Electronic Transactions on Numerical Analysis},
  pages =	 {54--82},
  year={2009}
}

@inproceedings{SH22a,
  title={Long-tail Mixup for Extreme Multi-label Classification},
  author={Han, Sangwoo and Choi, Eunseong and Lim, Chan and Shim, Hyunjung and Lee, Jongwuk},
  booktitle={Proceedings of the 31st ACM International Conference on Information and Knowledge Management (CIKM)},
  pages={3998--4002},
  year={2022}
}


@article{MH09b,
  title={{PyMVPA: A Python toolbox for multivariate pattern analysis of fMRI data}},
  author={Michael Hanke and Yaroslav O. Halchenko and
Per B. Sederberg and Stephen Jos\'{e} Hanson and
James V. Haxby and Stefan Pollmann},
  journal={Neuroinformatics},
  volume={7},
  number={1},
  pages={37--53},
  issn={1539-2791},
  year={2009},
  publisher={Springer}
}

@inproceedings{SH88a,
  author    = {Hanson, Stephen and Pratt, Lorien},
  title     = {Comparing biases for minimal network construction with back-propagation},
  booktitle = {Advances in Neural Information Processing Systems},
  volume    = {1},
  year      = {1988},
}


@article{CRH20a,
  title={Array programming with {NumPy}},
  author={Harris, Charles R. and Millman, K. Jarrod and van der Walt, St{\'e}fan J. and Gommers, Ralf and Virtanen, Pauli and Cournapeau, David and Wieser, Eric and Taylor, Julian and Berg, Sebastian and Smith, Nathaniel J and others},
  journal={Nature},
  volume={585},
  number={7825},
  pages={357--362},
  year={2020}
}

@article{CRH20a-short,
  title={Array programming with {NumPy}},
  author={Harris, Charles R. and Millman, K. Jarrod and van der Walt, St{\'e}fan J. and Gommers, Ralf and Virtanen, Pauli and Cournapeau, David and Wieser, Eric and Taylor, Julian and Berg, Sebastian and Smith, Nathaniel J and others},
  journal={Nature},
  volume={585},
  pages={357--362},
  year={2020}
}


@Article{ZH54a,
        author = {Harris, Zellig S.},
        title = {Distributional Structure},
        journal = {Word},
        volume = {10},
        issue = {2/3},
        year = {1954},
        pages = {146-162}
}

@misc{DH21a,
      title={A Brief Introduction to Automatic Differentiation for Machine Learning},
      author={Davan Harrison},
      year={2021},
      eprint={2110.06209},
      archivePrefix={arXiv},
      primaryClass={cs.LG}
}

@Article{TH98a,
  author = 	 {Trevor Hastie and Robert Tibshirani},
  title = 	 {Classification by pairwise
coupling},
  journal = 	 {The Annals of Statistics},
  year = 	 {1998},
  volume =	 {26},
  number =	 {1},
  pages =	 {451--471}
}

@Article{TH98a-short,
  author = 	 {Trevor Hastie and Robert Tibshirani},
  title = 	 {Classification by pairwise
coupling},
  journal = 	 {Ann. Statist.},
  year = 	 {1998},
  volume =	 {26},
  number =	 {1},
  pages =	 {451--471}
}


@InCollection{TH98b,
  author = 	 {Trevor Hastie and Robert Tibshirani},
  title = 	 {Classification by pairwise
coupling},
  booktitle = "Advances in Neural Information Processing Systems 10",
  OPTpages = 	 {},
  publisher = "MIT Press",
  address   = "Cambridge, MA",
  year =	 {1998},
  editor =	 {M. I. Jordan and M. J. Kearns and S. A. Solla},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTtype = 	 {},
  OPTchapter = 	 {},
  OPTaddress = 	 {},
  OPTedition = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@InCollection{TH98b-short,
  author = 	 {Trevor Hastie and Robert Tibshirani},
  title = 	 {Classification by pairwise
coupling},
  booktitle = "{NIPS} 10",
  year =	 {1998}
}

@book{TH02,
  author =	{Trevor Hastie and Robert Tibshirani and J. Friedman},
  title =	{The Elements of Statistical Learning: Data Mining, Inference, and Prediction},
  publisher =	{Springer},
  edition =	{Second},
  year =	{2009}
}

@article{TH04a,
	author = {Hastie, Trevor and Rosset, Saharon and Tibshirani, Robert and Zhu, Ji},
	title = {The Entire Regularization Path for the Support Vector Machine},
	journal = {Journal of Machine Learning Research},
	volume = {5},
	year = {2004},
	pages = {1391--1415}
}

@article{TH04a-short,
	author = {Hastie, Trevor and Rosset, Saharon and Tibshirani, Robert and Zhu, Ji},
	title = {The Entire Regularization Path for the Support Vector Machine},
	journal = {JMLR},
	volume = {5},
	year = {2004},
	pages = {1391--1415}
}


@Article{RJH93a,
  author = 	 {R. J. Hathaway and J. C. Bezdek},
  title = 	 {Switching regression models and fuzzy clustering},
  journal = 	 {IEEE Transactions on Fuzzy Systems},
  year = 	 {1993},
  volume =	 {1},
  number =       {3},
  pages =	 {195--204}
}

@Book{SH99a,
  author =	 "Simon Haykin",
  title =	 "Neural Networks : {A} Comprehensive Foundation",
  publisher =	 "Prentice Hall",
  address =	 "New Jersey",
	edition = "2nd",
  year =	 "1999",
}


@Article{SH91a,
  author = 	 {S. Haykin and D. Cong},
  title = 	 {Classification of radar clutter using neural networks},
  journal = 	 {IEEE Transactions on Neural Networks},
  year = 	 {1991},
  volume =	 {2},
  pages =	 {589--600}
}

@ARTICLE{HH09a,
  author={He, Haibo and Garcia, Edwardo A.},
  journal={IEEE Transactions on Knowledge and Data Engineering}, 
  title={Learning from imbalanced data}, 
  year={2009},
  mon=sep,
  volume={21},
  number={9},
  pages={1263--1284}
}

@InProceedings{KH15a,
author = {He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian},
title = {Delving Deep into Rectifiers: Surpassing Human-Level
Performance on {I}mage{N}et Classification},
booktitle = {Proceedings of IEEE International Conference on Computer Vision (ICCV)},
year = {2015}
}

@InProceedings{KH15a-short,
author = {He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian},
title = {Delving Deep into Rectifiers: Surpassing Human-Level
Performance on {I}mage{N}et Classification},
booktitle = {ICCV},
year = {2015}
}

@inproceedings{RH16a,
  title={Ups and downs: Modeling the visual evolution of fashion trends with one-class collaborative filtering},
  author={He, Ruining and McAuley, Julian},
  booktitle={Proceedings of the 25th International Conference on World Wide Web (WWW)},
  pages={507--517},
  year={2016}
}

@misc{XH16a,
  title={Large Scale Distributed {H}essian-Free Optimization for Deep Neural Network},
  author={He, Xi and Mudigere, Dheevatsa and Smelyanskiy, Mikhail and Tak{\'a}{\v{c}}, Martin},
  booktitle={AAAI-17 Workshop on Distributed Machine Learning},
  year={2017}
}

@inproceedings{XH16b,
  title={Fast matrix factorization for online recommendation with implicit feedback},
  author={He, Xiangnan and Zhang, Hanwang and Kan, Min-Yen and Chua, Tat-Seng},
  booktitle={Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval},
  pages={549--558},
  year={2016}
}

@inproceedings{XH16b-short,
  title={Fast matrix factorization for online recommendation with implicit feedback},
  author={He, Xiangnan and Zhang, Hanwang and Kan, Min-Yen and Chua, Tat-Seng},
  booktitle={SIGIR},
  year={2016}
}

@inproceedings{XH14a,
 author = {He, Xinran and Pan, Junfeng and Jin, Ou and Xu, Tianbing and Liu, Bo and Xu, Tao and Shi, Yanxin and Atallah, Antoine and Herbrich, Ralf and Bowers, Stuart and Candela, Joaquin Qui{\~{n}}onero},
 title = {Practical Lessons from Predicting Clicks on Ads at {F}acebook},
 booktitle = {Proceedings of the Eighth International Workshop on Data Mining for Online Advertising (ADKDD)},
 year = {2014},
 pages = {5:1--5:9}
} 

@inproceedings{XH14a-short,
 author = {He, Xinran and Pan, Junfeng and Jin, Ou and Xu, Tianbing and Liu, Bo and Xu, Tao and Shi, Yanxin and Atallah, Antoine and Herbrich, Ralf and Bowers, Stuart and Candela, Joaquin Qui{\~{n}}onero},
 title = {Practical Lessons from Predicting Clicks on Ads at {F}acebook},
 booktitle = {ADKDD},
 year = {2014}
} 

@inproceedings{YH19b,
author = {He, Yu and Song, Yangqiu and Li, Jianxin and Ji, Cheng and Peng, Jian and Peng, Hao},
title = {Hete{S}pacey{W}alk: A Heterogeneous Spacey Random Walk for Heterogeneous Information Network Embedding},
year = {2019},
booktitle = {Proceedings of the 28th ACM International Conference on Information and Knowledge Management (CIKM)},
pages = {639--648}
}

@article{JJH79a,
title={Sample selection bias as a specification error},
author={Heckman, James J.},
journal={Econometrica},
volume={47},
number={1},
pages={153--161},
year={1979}
}

@article{DAH04a,
  title={A Disquisition on the Performance Behavior of Binary Search Tree Data Structures},
  author={Heger, Dominique A.},
  journal={European Journal for the Informatics Professional},
  volume={5},
  number={5},
  pages={67--75},
  year={2004}
}

@MastersThesis{MH01a,
  author = {Matthias Heiler},
  title =  {Optimization Criteria and Learning Algorithms for Large Margin Classifiers},
  school = {University of Mannheim, Germany},
  year =   {2001},
  address ={Department of Mathematics and Computer Science, Computer Vision, Graphics, and Pattern Recognition Group, D-68131 Mannheim, Germany}
}



@techreport{MH97,
author      = {Matthias Heinkenschloss and Michael Ulbrich and Stefan Ulbrich},
title       = {Superlinear and quadratic convergence of affine-scaling
               interior-point {N}ewton methods for problems with
               simple bounds without strict complementarity assumption},
institution = {Rice University},
number      = {TR97-30},
address     = {Houston, Texas},
type        = {Technical Report},
year        = {1997},
}

@article{CH96a,
author     = {C. Helmberg and F. Rendl and  B. Vanderbei and H. Wolkowicz},
journal    = {SIAM J. Optim.},
pages      = {342--361},
title      = {An interior-point method for semidefinite programming},
volume     = {6},
year       = {1996}
}

@InProceedings{CH96b,
  author = 	 {C. Helmberg and F. Rendl and R. Weismantel},
  title = 	 {Quadratic Knapsack Relaxations Using Cutting Planes and Semidefinite Programming},
  booktitle = 	 {Proceedings of the 5th International IPCO
   Conference, Vancouver,},
  editor =	 {W. H. Cunningham and S. T. McCormick and M. Queyranne},
  number =	 {1084},
  series =	 {Lecture Notes in Computer Science},
  year =	 {1996},
  publisher =	 {Springer},
  pages =	 {175--189}
}

@article{DH16a,
  title={Gaussian error linear units ({GELU}s)},
  author={Hendrycks, Dan and Gimpel, Kevin},
  journal={arXiv preprint arXiv:1606.08415},
  year={2016}
}

@article{PH12a,
  title={Entropy search for information-efficient global optimization},
  author={Hennig, Philipp and Schuler, Christian J},
  journal={Journal of Machine Learning Research},
  volume={13},
  pages={1809--1837},
  year={2012}
}


@misc{JFH18a,
  author    = {Jo{\~{a}}o F. Henriques and
               S{\'{e}}bastien Ehrhardt and
               Samuel Albanie and
               Andrea Vedaldi},
  title     = {Small steps and giant leaps: Minimal {N}ewton solvers for Deep Learning},
  note={arXiv preprint 1805.08095},
  year={2018}
}

@incollection{RH00a,
 author = {Herbrich, Ralf and Graepel, Thore and Obermayer, Klaus},
 title = {Large Margin Rank Boundaries for Ordinal Regression},
 booktitle = {Advances in Large Margin Classifiers},
 editor = {Bartlett, Peter J. and Sch\"{o}lkopf, Bernhard and Schuurmans, Dale and Smola, Alexander J.},
 pages={115--132},
 year={2000},
 publisher={MIT Press}
}

@InProceedings{OHSUMED94,
  author = {William Hersh and Chris Buckley and TJ Leone and David Hickam},
  title = {{OHSUMED}: An Interactive Retrieval Evaluation and New Large Test
Collection for Research},
  booktitle = {Proceedings of SIGIR-94},
  year = {1994},
  pages = {192--201}
}

@InProceedings{OHSUMED94-short,
  author = {William Hersh and Chris Buckley and TJ Leone and David Hickam},
  title = {{OHSUMED}: An Interactive Retrieval Evaluation and New Large Test
Collection for Research},
  booktitle = {SIGIR},
  year = {1994}
}

@incollection{RH06a,
  author = 	 {Ralf Herbrich and Tom Minka and Thore Graepel},
  title = 	 {True{S}kill{$^{\rm {TM}}$}: A {B}ayesian Skill Rating System},
  booktitle = "Advances in Neural Information Processing Systems 19",
  publisher = "MIT Press",
  address = "Cambridge, MA",
  year = "2007"
  }

@incollection{RH06a-short,
  author = 	 {Ralf Herbrich and Tom Minka and Thore Graepel},
  title = 	 {TrueSkill{$^{\rm {TM}}$}: A {B}ayesian Skill Rating System},
  booktitle = "{NIPS} 19",
  year = "2007"
  }

@Article{MRH52a,
  title={Methods of Conjugate Gradients for Solving Linear Systems},
  author={Hestenes, Magnus Rudolph and Stiefel, Eduard},
  volume={49},
  number={1},
  pages ={409--436},
  year={1952},
  journal = {Journal of Research of the National Bureau of Standards}
}

@Article{MRH52a-short,
  title={Methods of Conjugate Gradients for Solving Linear Systems},
  author={Hestenes, Magnus Rudolph and Stiefel, Eduard},
  volume={49},
  pages ={409--436},
  year={1952},
  journal ={JRNBS}
}


@Article{DJH99a,
  author =       "Desmond J. Higham",
  title =        "Trust Region Algorithms and Timestep Selection",
  journal =      "SIAM Journal on Numerical Analysis",
  volume =       "37",
  number =       "1",
  pages =        "194--210",
  month =        "November",
  year =         "1999",
  ISSN =         "0036-1429 (print), 1095-7170 (electronic)",
  bibsource =    "http://epubs.siam.org/sam-bin/dbq/toc/SINUM/37/1",
  URL =          "http://epubs.siam.org/sam-bin/dbq/article/33597.html"
}

@article{CH57a,
  author={Clifford Hildreth},
  title={A quadratic programming procedure},
  journal={Naval Research Logistics Quarterly},
  volume={4},
  pages={79--85},
  year={1957}
}

@article{CH57a-short,
  author={Clifford Hildreth},
  title={A quadratic programming procedure},
  journal={Naval Res. Logist.},
  volume={4},
  pages={79--85},
  year={1957}
}

@article{GEH06a,
  title={Reducing the dimensionality of data with neural networks},
  author={Hinton, Geoffrey E. and Salakhutdinov, Ruslan R.},
  journal={Science},
  volume={313},
  number={5786},
  pages={504--507},
  year={2006}
}

@article{GEH12a,
  author={Geoffrey E. Hinton and Li Deng and Dong Yu and George Dahl and Abdel-rahman Mohamed and Navdeep Jaitly and Andrew Senior and Vincent Vanhoucke and Patrick Nguyen and Tara Sainath and Brian Kingsbury},
  journal={IEEE Signal Processing Magazine},
  title={Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups},
  year={2012},
  volume={29},
  number={6},
  pages={82-97}
}


@Article{HSH01a,
  author = 	 {Henrique Steinherz Hippert and Carlos Eduardo Pedreira and Reinaldo Castro Souza},
  title = 	 {Neural networks for short-term load forecasting: a review and evaluation},
  journal = 	 {IEEE Transactions on Power Systems},
  year = 	 {2001},
  volume =	 {16},
  number =	 {1},
  pages =	 {44--55}
}


@article{IH97,
author      = {I. Hlad\'{i}k and M. B. Reed and G. Swoboda},
journal     = {Int. J. Num. Meth. Eng.},
pages       = {2109--2117},
title       = {Robust preconditioners for linear elasticity {FEM} analysis},
year        = {1997},
volume      = {40}
}


@inproceedings{CHH10a,
   author    = {Chia-Hua Ho and Ming-Hen Tsai and Chih-Jen Lin},
   title     = {Active Learning and Experimental Design with {SVM}s},
  booktitle = 	 {JMLR Workshop and Conference Proceedings: Workshop on Active Learning and Experimental Design},
   year      = {2011},
   pages     = {71--84},
  volume =	 {16},
  url = {http://www.csie.ntu.edu.tw/~cjlin/papers/activelearning/activelearning.pdf}
}

@Article{CHH12a,
  author = {Chia-Hua Ho and Chih-Jen Lin},
  title = {Large-scale Linear Support Vector Regression},
  year = 	 {2012},
  journal = 	 {Journal of Machine Learning Research},
  volume =	 {13},
  OPTnumber = 	 {},
  pages =	 {3323-3348},
  url={http://www.csie.ntu.edu.tw/~cjlin/papers/linear-svr.pdf}
}

@Article{CHH12a-short,
 author = {Chia-Hua Ho and Chih-Jen Lin},
 title = {Large-scale Linear Support Vector Regression},
 year =   {2012},
 journal =  {JMLR},
 volume =  {13},
 pages =   {3323-3348}
}


@incollection{QH13a,
title = {More effective distributed {M}L via a stale synchronous parallel parameter server},
author = {Ho, Qirong and Cipar, James and Cui, Henggang and Lee, Seunghak and Kim, Jin Kyu and Gibbons, Phillip B. and Gibson, Garth A and Ganger, Greg and Xing, Eric},
booktitle = {Advances in Neural Information Processing Systems 26},
pages = {1223--1231},
year = {2013}
}

@InProceedings{TKH96a,
  author = 	 {Tin Kam Ho and
 Eugene M. Kleinberg},
  title = 	 {Building Projectable Classifiers of Arbitrary Complexity},
  booktitle = 	 {Proceedings of the 13th {I}nternational {C}onference
     on {P}attern {R}ecognition},
  pages =	 {880--885},
  year =	 {1996},
  address =	 {Vienna, Austria},
  month =	 {August}
}

@article{CARH61a,
  title={Algorithm 63: partition},
  author={Hoare, Charles Antony Richard},
  journal={Communications of the ACM},
  volume={4},
  number={7},
  pages={321},
  year={1961}
}

@article{CARH61b,
  title={Algorithm 65: find},
  author={Hoare, Charles Antony Richard},
  journal={Communications of the ACM},
  volume={4},
  number={7},
  pages={321--322},
  year={1961}
}

@article{AEH70a,
  title={Ridge Regression: Biased Estimation for Nonorthogonal Problems},
  author={Arthur E. Hoerl and Robert W. Kennard},
  journal={Technometrics},
  volume={12},
  number={1},
  pages={55--67},
  year={1970}
}

@article{AJH52a,
title={On approximate solutions of systems of linear inequalities},
author={Hoffman, Alan J},
journal={Journal of Research of the National Bureau of Standards},
volume={49},
number={4},
pages={263--265},
year={1952}
}

@article{HOGG,
author      = {R. V. Hogg},
journal     = {Journal of the American Statistical Association},
pages       = {422--424},
title       = {More light on the kurtosis and related statistics},
year        = {1972},
volume      = {67}
}


@article{ho:un,
author      = {T. Hofmann and J. Puzicha and J. M. Buhmann},
journal     = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
pages       = {803--818},
title       = {Unsupervised texture segmentation in a deterministic annealing framework},
year        = {1998},
volume      = {20},
number      = {8}
}

@book{JHH92a,
 author = {Holland, John Henry},
 title = {Adaptation in Natural and Artificial Systems},
 year = {1992},
 publisher = {MIT Press}
}

@misc{MH14a,
author={Hong, Mingyi and Chang, Tsung-Hui and Wang, Xiangfeng and
Razaviyayn, Meisam and Ma, Shiqian and Luo, Zhi-Quan},
title={A Block Successive Upper Bound Minimization Method of Multipliers for
Linearly Constrained Convex Optimization},
note={arXiv preprint arXiv:1401.7079},
year={2014}
}

@book{RAH12a,
  title={Matrix analysis},
  author={Horn, Roger A. and Johnson, Charles R.},
  year={2012},
  publisher={Cambridge university press}
}

@article{KH12a,
  title={Spherical k-means clustering},
  author={Hornik, Kurt and Feinerer, Ingo and Kober, Martin and Buchta, Christian},
  journal={Journal of statistical software},
  volume={50},
  pages={1--22},
  year={2012}
}

@article{DGH52a,
author = {Horvitz, Daniel G. and Thompson, Donovan J.},
year = {1952},
pages = {663-685},
title = {A Generalization of Sampling Without Replacement From a Finite Universe},
volume = {47},
journal = {Journal of the American Statistical Association}
}

@article{DGH52a-short,
author = {Horvitz, Daniel G. and Thompson, Donovan J.},
year = {1952},
pages = {663-685},
title = {A Generalization of Sampling Without Replacement From a Finite Universe},
volume = {47},
journal = {J. Amer. Statist. Assoc.}
}

@inproceedings{YH19a,
author = {Hou, Yifan and Chen, Hongzhi and Li, Changji and Cheng, James and Yang, Ming-Chang},
title = {A Representation Learning Framework for Property Graphs},
year = {2019},
booktitle = {Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)},
pages = {65--73}
}

@InProceedings{POH02a,
  author = 	 {Patrik O. Hoyer},
  title = 	 {Non-negative sparse coding},
  booktitle = 	 {Proceedings of IEEE Workshop on Neural Networks for Signal Processing},
  OPTcrossref =  {},
  OPTkey = 	 {},
  pages =	 {557--565},
  year =	 {2002},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTaddress = 	 {},
  OPTmonth = 	 {},
  OPTorganization = {},
  OPTpublisher = {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@InProceedings{POH02a-short,
  author = 	 {Patrik O. Hoyer},
  title = 	 {Non-negative sparse coding},
  booktitle = 	 {IEEE NNSP},
  year =	 {2002},
}

@Article{POH04a,
  author = 	 {Patrik O. Hoyer},
  title = 	 {Non-negative Matrix Factorization with sparseness constraints},
  journal = 	 {Journal of Machine Learning Research},
  year = 	 {2004},
  OPTkey = 	 {},
  volume =	 {5},
  OPTnumber = 	 {},
  pages =	 {1457--1469},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@Article{POH04a-short,
  author = 	 {Patrik O. Hoyer},
  title = 	 {Non-negative Matrix Factorization with sparseness constraints},
  journal = 	 {JMLR},
  year = 	 {2004},
  OPTkey = 	 {},
  volume =	 {5},
  OPTnumber = 	 {},
  pages =	 {1457--1469},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@Inproceedings{CYH17a,
 author = {Chih-Yang Hsia and Ya Zhu and Chih-Jen Lin},
 title = {A Study on Trust Region Update Rules in {N}ewton Methods for Large-scale Linear Classification},
 booktitle = {Proceedings of the {A}sian Conference on Machine Learning ({ACML})},
 year = {2017},
 url={http://www.csie.ntu.edu.tw/~cjlin/papers/newtron/newtron.pdf}
}

@Inproceedings{CYH17a-short,
 author = {Chih-Yang Hsia and Ya Zhu and Chih-Jen Lin},
 title = {A Study on Trust Region Update Rules in {N}ewton Methods for Large-scale Linear Classification},
 booktitle = {{ACML}},
 year = {2017}
}

@Inproceedings{CYH17b,
author = {Chih-Yang Hsia and Wei-Lin Chiang and Chih-Jen Lin},
title = {Preconditioned Conjugate Gradient Methods in Truncated {N}ewton Frameworks for Large-scale Linear Classification},
 booktitle = {Proceedings of the Asian Conference on Machine Learning (ACML)},
 year = {2018},
 url={http://www.csie.ntu.edu.tw/~cjlin/papers/tron_pcg/precondition.pdf}
}

@Inproceedings{CYH17b-short,
author = {Chih-Yang Hsia and Wei-Lin Chiang and Chih-Jen Lin},
title = {Preconditioned Conjugate Gradient Methods in Truncated {N}ewton Frameworks for Large-scale Linear Classification},
 booktitle = {ACML},
 year = {2018}
}


@Article{JYH19a,
  author = 	 {Jui-Yang Hsia and Chih-Jen Lin},
  title = 	 {Parameter Selection for Linear Support Vector Regression},
  journal = 	 {IEEE Transactions on Neural Networks and Learning Systems},
  year = 	 {2020},
  url =	 {https://www.csie.ntu.edu.tw/~cjlin/libsvmtools/warm-start/svr-param.pdf},  
  OPTkey = 	 {},
  volume =	 {31},
  OPTnumber = 	 {},
  pages =	 {5639--5644},
  OPTmonth = 	 {},
  OPTannote = 	 {}
}

@inproceedings{CYH18a,
  author    = {Cheng-Yu Hsieh and
               Yi-An Lin and
               Hsuan-Tien Lin},
  title     = {A Deep Model With Local Surrogate Loss for General Cost-Sensitive
               Multi-Label Learning},
  booktitle = {Proceedings of the Thirty-Second {AAAI} Conference on Artificial Intelligence (AAAI)},
  pages     = {3239--3246},
  year      = {2018}
}

@inproceedings{CJH08a,
author = {Cho-Jui Hsieh and Kai-Wei Chang and Chih-Jen Lin and S.
Sathiya Keerthi and Sellamanickam Sundararajan},
title = {A dual coordinate descent method for large-scale linear {SVM}},
  booktitle = {Proceedings of the Twenty Fifth International Conference on
               Machine Learning (ICML)},
  year =     {2008},
  url =	 {http://www.csie.ntu.edu.tw/~cjlin/papers/cddual.pdf},
  OPTkey =   {},
  OPTtype =      {},
  OPTnumber =    {},
  OPTaddress =   {},
  OPTmonth =     {},
  OPTannote =    {}
}
%   note = {Software available at \url{http://www.csie.ntu.edu.tw/~cjlin/liblinear}},

@inproceedings{CJH08a-short,
author = {C.-J. Hsieh and K.-W. Chang and C.-J. Lin and S.
S. Keerthi and S. Sundararajan},
title = {A dual coordinate descent method for large-scale linear {SVM}},
  booktitle = {ICML},
  year      = {2008}
}

@inproceedings{CJH11a,
  author = {Cho-Jui Hsieh and Inderjit S. Dhillon},
  title = {Fast Coordinate Descent Methods with Variable Selection for Non-negative Matrix Factorization},
  booktitle = {Proceedings of the Seventeenth ACM SIGKDD International
Conference on Knowledge Discovery and Data Mining},
  year = {2011}
}

@inproceedings{CJH11a-short,
  author = {Cho-Jui Hsieh and Inderjit S. Dhillon},
  title = {Fast Coordinate Descent Methods with Variable Selection for Non-negative Matrix Factorization},
  booktitle = {KDD},
  year = {2011}
}

@inproceedings{CJH11b,
  author = {Cho-Jui Hsieh and Matyas A. Sustik and Pradeep Ravikumar and Inderjit S. Dhillon},
  title = {Sparse Inverse Covariance Matrix Estimation Using Quadratic Approximation},
  booktitle = {Advances in Neural Information Processing Systems (NIPS) 24},
  year = {2011}
}

@inproceedings{CJH15a,
  author    = {Cho-Jui Hsieh and Hsiang-Fu Yu and Inderjit S. Dhillon},
  title     = {{PASSCoDe: Parallel asynchronous stochastic dual coordinate descent}},
  booktitle = {Proceedings of the Thirty Second International Conference on
               Machine Learning (ICML)},
  year      = {2015}
}

@inproceedings{CJH15a-short,
  author    = {Cho-Jui Hsieh and Hsiang-Fu Yu and Inderjit S. Dhillon},
  title     = {{PASSCoDe: Parallel asynchronous stochastic dual coordinate descent}},
  booktitle = {ICML},
  year      = {2015}
}

@inproceedings{CJH15b, 
   title={{PU} Learning for Matrix Completion}, 
   Author={Hsieh, Cho-Jui and Natarajan, Nagarajan and Dhillon, Inderjit}, 
   year="2015", 
   Booktitle="Proceedings of the 32nd International Conference on Machine Learning (ICML)", 
   pages="2445-2453" 
} 

@inproceedings{CJH15b-short,
   title={{PU} Learning for Matrix Completion}, 
   Author={Hsieh, Cho-Jui and Natarajan, Nagarajan and Dhillon, Inderjit}, 
   year="2015", 
   Booktitle={ICML}
} 

@TechReport{CWH03a,
  author = 	 {Chih-Wei Hsu and Chih-Chung Chang and Chih-Jen Lin},
  title = 	 {A practical guide to support vector classification},
  institution =  {Department of Computer Science, National Taiwan University},
  url =	 {http://www.csie.ntu.edu.tw/~cjlin/papers/guide/guide.pdf},
  year = 	 {2003}
}

@TechReport{CWH03a-short,
  author = 	 {Chih-Wei Hsu and Chih-Chung Chang and Chih-Jen Lin},
  title = 	 {A practical guide to support vector classification},
  institution =  {National Taiwan University},
  url =	 {http://www.csie.ntu.edu.tw/~cjlin/papers/guide/guide.pdf},
  year = 	 {2003}
}

@Article{CWH01a,
  author = 	 {Chih-Wei Hsu and Chih-Jen Lin},
  title = 	 {A Comparison of Methods 
for Multi-class Support Vector Machines},
  journal={IEEE Transactions on Neural Networks},
  volume={13},
  number={2},
  pages={415--425},
  year = 	 {2002}
}

@Article{CWH01a-short,
  author = 	 {Chih-Wei Hsu and Chih-Jen Lin},
  title = 	 {A Comparison of Methods 
for Multi-class Support Vector Machines},
  journal={IEEE TNN},
  volume={13},
  number={2},
  pages={415--425},
  year = 	 {2002}
}


@Article{CWH01b,
  author = 	 {Chih-Wei Hsu and Chih-Jen Lin},
  title = 	 {A simple decomposition method for 
 support vector machines},
  year = 	 {2002},
  journal = {Machine Learning},
  volume = {46},
  pages = {291--314}
}



@InCollection{DH11a,
  author =	 {Daniel Hsu and Nikos Karampatziakis and John Langford},
  editor =	 {Ron Bekkerman and Misha Bilenko and John Langford},
  title = 	 {Parallel Online Learning},
  chapter = 	 {14},
  publisher = 	 {Cambridge University Press},
  year = 	 {2011},
  booktitle = 	 {Scaling Up Machine Learning},
  OPTcrossref =  {},
  OPTkey = 	 {},
  OPTpages = 	 {},
  OPTpublisher = {},
  OPTyear = 	 {},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTtype = 	 {},
  OPTchapter = 	 {},
  OPTaddress = 	 {},
  OPTedition = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}


@ONLINE{HTC13a,
	author = {HTC},
	title = {The new HTC One},
        howpublished = {\url{http://www.htc.com/}}	
}

@ONLINE{HTC14a,
author = {HTC},
title = {{HTC} {R}esearch},
howpublished = {\url{http://research.htc.com/2014/06/publication14001/}}
}

@inproceedings{LH13a,
  title={Personalized recommendation via cross-domain triadic factorization},
  author={Hu, Liang and Cao, Jian and Xu, Guandong and Cao, Longbing and Gu, Zhiping and Zhu, Can},
  booktitle={Proceedings of the 22nd International Conference on World Wide Web (WWW)},
  pages={595--606},
  year={2013}
}

@inproceedings{LH13a-short,
  title={Personalized recommendation via cross-domain triadic factorization},
  author={Hu, Liang and Cao, Jian and Xu, Guandong and Cao, Longbing and Gu, Zhiping and Zhu, Can},
  booktitle={WWW},
  year={2013}
}

@INPROCEEDINGS{YH08a,
    author = {Yifan Hu and Yehuda Koren and Chris Volinsky},
    title = {Collaborative filtering for implicit feedback datasets},
 booktitle = {Proceedings of the IEEE International Conference on Data Mining (ICDM)},
    year = {2008},
    pages = {263--272}
}

@INPROCEEDINGS{YH08a-short,
    author = {Yifan Hu and Yehuda Koren and Chris Volinsky},
    title = {Collaborative filtering for implicit feedback datasets},
 booktitle = {ICDM},
    year = {2008}
}

@inproceedings{ZH19a,
  title={Unbiased {L}ambda{MART}: An unbiased pairwise learning-to-rank algorithm},
  author={Hu, Ziniu and Wang, Yang and Peng, Qu and Li, Hang},
  booktitle={Proceedings of The Web Conference},  
  pages={2830--2836},
  year={2019}
}

@inproceedings{ZH19a-short,
  title={Unbiased {L}ambda{MART}: An unbiased pairwise learning-to-rank algorithm},
  author={Hu, Ziniu and Wang, Yang and Peng, Qu and Li, Hang},
  booktitle={WWW},  
  year={2019}
}

@InProceedings{AH10a,
	title={Identifying Correction Rules for Auto Editing},
	author={Anta Huang and Tsung-Ting Kuo and Ying-Chun Lai and Shou-De Lin},
        booktitle = {Proceedings of the 
22nd Conference on Computational Linguistics and Speech Processing},
	year={2010}
}

@inproceedings{CWH22a,
title = "{PLM}-{ICD}: Automatic {ICD} Coding with Pretrained Language Models",
author = "Huang, Chao-Wei  and
  Tsai, Shang-Chi  and
  Chen, Yun-Nung",
editor = "Naumann, Tristan  and
  Bethard, Steven  and
  Roberts, Kirk  and
  Rumshisky, Anna",
booktitle = "Proceedings of the Fourth Clinical Natural Language Processing Workshop",
year = "2022",
doi = "10.18653/v1/2022.clinicalnlp-1.2",
pages = "10--20",
}

@article{CMH07a,
  title={Model selection for support vector machines via uniform design},
  author={Huang, Chien-Ming and Lee, Yuh-Jye and Lin, Dennis KJ and Huang, Su-Yun},
  journal={Computational Statistics and Data Analysis},
  volume={52},
  number={1},
  pages={335--346},
  year={2007}
}

@InProceedings{FLH09a,
  author =       {Fang-Lan Huang and Cho-Jui Hsieh and Kai-Wei Chang
and Chih-Jen Lin},
  title =        {Iterative Scaling and Coordinate Descent Methods for
Maximum Entropy},
  booktitle =    {Proceedings of the 47th Annual Meeting of the
Association of Computational Linguistics (ACL)},
  year =         {2009},
  note =         {Short paper}
}

@Article{FLH09b,
  author = {Fang-Lan Huang and Cho-Jui Hsieh and Kai-Wei Chang and Chih-Jen Lin},
  title = {Iterative Scaling and Coordinate Descent Methods for Maximum Entropy},
  journal = {Journal of Machine Learning Research},
  volume      = {11},
  pages={815--848},
  year = {2010},
  url =	 {http://www.csie.ntu.edu.tw/~cjlin/papers/maxent_journal.pdf}
}

@Article{FLH09b-short,
  author = {Fang-Lan Huang and Cho-Jui Hsieh and Kai-Wei Chang and Chih-Jen Lin},
  title = {Iterative Scaling and Coordinate Descent Methods for Maximum Entropy},
  journal = {JMLR},
  year = {2010}
}


@InProceedings{HYH16a,
  author = 	 {Hsin-Yuan Huang and Chih-Jen Lin},
  title = 	 {Linear and Kernel Classification: When to Use Which?},
  OPTcrossref =  {},
  OPTkey = 	 {},
  booktitle =	 {Proceedings of SIAM International Conference on Data Mining (SDM)},
  year =	 {2016},
  url =	 {http://www.csie.ntu.edu.tw/~cjlin/papers/kernel-check/kcheck.pdf},  
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTpages = 	 {},
  OPTmonth = 	 {},
  OPTaddress = 	 {},
  OPTorganization = {},
  OPTpublisher = {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@incollection{JH07a,
title = {Correcting Sample Selection Bias by Unlabeled Data},
author = {Jiayuan Huang and Gretton, Arthur and Borgwardt, Karsten and Sch\"{o}lkopf, Bernhard and Alex J. Smola},
booktitle = {Advances in Neural Information Processing Systems 19},
editor = {B. Sch\"{o}lkopf and J. C. Platt and T. Hoffman},
pages = {601--608},
year = {2007}
}

@incollection{JH07a-short,
title = {Correcting Sample Selection Bias by Unlabeled Data},
author = {Jiayuan Huang and Gretton, Arthur and Borgwardt, Karsten and Sch\"{o}lkopf, Bernhard and Alex J. Smola},
booktitle = {NIPS},
year = {2007}
}

@inproceedings{JCH08a,
  title={Cumulative distribution networks and the derivative-sum-product algorithm},
  author={Huang, Jim C. and Frey, Brendan J.},
  booktitle={Proceedings of the Twenty-Fourth Conference on Uncertainty in Artificial Intelligence (UAI)},
  year={2008}
}

@inproceedings{JTH20a,
  title={Embedding-based Retrieval in {F}acebook Search},
  author={Huang, Jui-Ting and Sharma, Ashish and Sun, Shuying and Xia, Li and Zhang, David and Pronin, Philip and Padmanabhan, Janani and Ottaviano, Giuseppe and Yang, Linjun},
  booktitle={Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)},
  pages={2553--2561},
  year={2020}
}

@inproceedings{JTH20a-short,
  title={Embedding-based Retrieval in {F}acebook Search},
  author={Huang, Jui-Ting and Sharma, Ashish and Sun, Shuying and Xia, Li and Zhang, David and Pronin, Philip and Padmanabhan, Janani and Ottaviano, Giuseppe and Yang, Linjun},
  booktitle={KDD},
  year={2020}
}

@inproceedings{PSH13a,
  title={Learning deep structured semantic models for web search using clickthrough data},
  author={Huang, Po-Sen and He, Xiaodong and Gao, Jianfeng and Deng, Li and Acero, Alex and Heck, Larry},
  booktitle={Proceedings of the 22nd ACM international conference on Information and Knowledge Management},
  pages={2333--2338},
  year={2013}
}

@inproceedings{PSH13a-short,
  title={Learning deep structured semantic models for web search using clickthrough data},
  author={Huang, Po-Sen and He, Xiaodong and Gao, Jianfeng and Deng, Li and Acero, Alex and Heck, Larry},
  booktitle={CIKM},
  year={2013}
}

@mastersthesis{TLH10a,
        author      = {Tian-Liang Huang},
        school      = {Department of Computer Science and Information Engineering, National Taiwan University},
        title       = {Comparison of {L}2-regularized Multi-class Linear Classifiers},
        year        = {2010}
} 


@inproceedings{TKH06a,
  author    = {Tzu-Kuo Huang   and Chih-Jen Lin and 
     Ruby C. Weng},
  title     = {Ranking individuals by group comparisons},
  booktitle = {Proceedings of the Twenty Third International Conference on
               Machine Learning (ICML)},
  year      = {2006}
}

@article{TKH08a,
  author    = {Tzu-Kuo Huang and Chih-Jen Lin and 
     Ruby C. Weng},
  title     = {Ranking individuals by group comparisons},
  journal = {Journal of Machine Learning Research},
  volume      = {9},
  pages={2187--2216},
  url =	 {http://www.csie.ntu.edu.tw/~cjlin/papers/genBTexp/genBTexp-jmlr.pdf},
  year      = {2008}
}

@inproceedings{TKH06a-short,
  author    = {Tzu-Kuo Huang   and Chih-Jen Lin and 
     Ruby C. Weng},
  title     = {Ranking individuals by group comparisons},
  booktitle = {ICML},
  year      = {2006}
}


@Article{TKH04a,
  author = 	 {Tzu-Kuo Huang and 
     Weng, Ruby C. and Chih-Jen Lin},
  title = 	 {Generalized {B}radley-{T}erry Models and Multi-class Probability Estimates},
  year = 	 {2006},
  journal = {Journal of Machine Learning Research},
  volume      = {7},
  pages={85--115},
  url =	 {http://www.csie.ntu.edu.tw/~cjlin/papers/generalBT.pdf},
  OPTkey = 	 {},
  OPTtype = 	 {},
  OPTnumber = 	 {},
  OPTaddress = 	 {},
  OPTmonth = 	 {},
  OPTannote = 	 {}
}

@Article{TKH04a-short,
  author = 	 {Tzu-Kuo Huang and 
     Ruby C. Weng  and Chih-Jen Lin},
  title = 	 {Generalized {B}radley-{T}erry Models and Multi-class Probability Estimates},
  year = 	 {2006},
  journal = {JMLR},
  volume      = {7},
  pages={85--115}
}


@incollection{TKH04b,
  author = 	 {Tzu-Kuo Huang and 
     Ruby C. Weng  and Chih-Jen Lin},
  title = 	 {A Generalized {B}radley-{T}erry Model: From Group Competition to
Individual Skill},
  booktitle = "Advances in Neural Information Processing Systems 17",
  publisher = "MIT Press",
  address = "Cambridge, MA",
  year = "2005"
  }
%  url =	 {http://www.csie.ntu.edu.tw/~cjlin/papers/generalBT.pdf}


@incollection{TKH04b-short,
  author = 	 {Tzu-Kuo Huang and 
     Ruby C. Weng  and Chih-Jen Lin},
  title = 	 {A Generalized {B}radley-{T}erry Model: From Group Competition to
Individual Skill},
  booktitle = "{NIPS} 17",
  year = "2005"
  }

@inproceedings{WH06a,
	title={Design of high performance {MVAPICH}2: {MPI}2 over
		InfiniBand},
	author={Huang, Wei and Santhanaraman, Gopalakrishnan and Jin,
		Hyun-Wook and Gao, Qi and Panda, Dhabaleswar K},
	booktitle={Sixth IEEE International Symposium on Cluster Computing and the Grid},
	volume={1},
	pages={43--48},
	year={2006},
	organization={IEEE}
}

@inproceedings{WH06a-short,
	title={Design of high performance {MVAPICH}2: {MPI}2 over
		InfiniBand},
	author={Huang, Wei and Santhanaraman, Gopalakrishnan and Jin,
		Hyun-Wook and Gao, Qi and Panda, Dhabaleswar K},
	booktitle={CCGrid},
	year={2006},
	organization={IEEE}
}

@article{XH19a,
  title={Label-aware Document Representation via Hybrid Attention for Extreme Multi-Label Text Classification}, 
  author={Xin Huang and Boli Chen and Lin Xiao and Liping Jing},
  year={2019},
  eprint={1905.10070},
  archivePrefix={arXiv},
  primaryClass={cs.LG}
}

@MastersThesis{YTH20a,
  author = {Yu-Ting Huang},
  title =  {{N}ewton Methods for Factorization Machines},
  school = {Department of Computer Science and Information Engineering, National Taiwan University},
  year = {2020},
  month ={April}
}

@inproceedings{ZH16a,
  title={{KB}-enabled query recommendation for long-tail queries},
  author={Huang, Zhipeng and Cautis, Bogdan and Cheng, Reynold and Zheng, Yudian},
  booktitle={Proceedings of the 25th ACM International on Conference on Information and Knowledge Management (CIKM)},
  pages={2107--2112},
  year={2016}
}

@inproceedings{ZH16a-short,
  title={{KB}-enabled query recommendation for long-tail queries},
  author={Huang, Zhipeng and Cautis, Bogdan and Cheng, Reynold and Zheng, Yudian},
  booktitle={CIKM},
  year={2016}
}

@inproceedings{IH16a,
 author = {Hubara, Itay and Courbariaux, Matthieu and Soudry, Daniel and El-Yaniv, Ran and Bengio, Yoshua},
 booktitle = {Advances in Neural Information Processing Systems},
 title = {Binarized Neural Networks},
 volume = {29},
 year = {2016},
pages = {4114--4122}
}

@inproceedings{IH16a-short,
 author = {Hubara, Itay and Courbariaux, Matthieu and Soudry, Daniel and El-Yaniv, Ran and Bengio, Yoshua},
 booktitle = {NIPS},
 title = {Binarized Neural Networks},
 year = {2016}
}

@article{DAH96a,
	author = {David A. Hull},
	title = {Stemming Algorithms -- A Case Study for Detailed Evaluation},
	journal = {JASIS},
	year = {1996},
	volume = {47},
	pages = {70--84}
}

@Article{JJH94a,
  author = 	 {J. J. Hull},
  title = 	 {A database for handwritten text recognition research},
  journal = 	 {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = 	 {1994},
  volume =	 {16},
  number =	 {5},
  pages =	 {550--554},
  month =	 {May}
}


@Article{DRH03a,
  author = 	 {David R. Hunter},
  title = 	 {{MM} algorithms for generalized {B}radley-{T}erry models},
  journal = 	 {The Annals of Statistics},
  year = 	 {2004},
  volume={32},
  pages={386--408}
}

@Article{DRH03a-short,
  author = 	 {David R. Hunter},
  title = 	 {{MM} algorithms for generalized {B}radley-{T}erry models},
  journal = 	 {Ann. Statist.},
  year = 	 {2004},
  volume={32},
  pages={386--408}
}



@Article{DH00a,
  author = 	 {Don Hush and Clint Scovel},
  title = 	 {Polynomial-time decomposition algorithms for support vector machines},
  year = 	 {2003},
  journal= {Machine Learning},
  volume={51},
  pages={51--71},
  url={http://www.c3.lanl.gov/~dhush/machine_learning/svm_decomp.ps}
}

@inproceedings{FH11a,
author="Hutter, Frank and Hoos, Holger H. and Leyton-Brown, Kevin",
editor="Coello, Carlos A. Coello",
title="Sequential Model-Based Optimization for General Algorithm Configuration",
booktitle="Learning and Intelligent Optimization",
year="2011",
pages="507--523"
}

@inproceedings{FH13a,
  title={An evaluation of sequential model-based optimization for expensive blackbox functions},
  author={Hutter, Frank and Hoos, Holger and Leyton-Brown, Kevin},
  booktitle={Proceedings of the 15th annual conference companion on Genetic and evolutionary computation},
  pages={1209--1216},
  year={2013}
}

@inproceedings{GI08a,
  title={Fast logistic regression for text categorization with variable-length n-grams},
  author={Ifrim, Georgiana and Bak{\i}r, G\"{o}khan and Weikum, Gerhard},
  booktitle = {Proceedings of the 14th ACM SIGKDD International
Conference on Knowledge Discovery and Data Mining},
  pages={354--362},
  year={2008}
}

@inproceedings{GI08a-short,
  title={Fast logistic regression for text categorization with variable-length n-grams},
  author={Ifrim, Georgiana and Bak{\i}r, G\"{o}khan and Weikum, Gerhard},
  booktitle = {KDD},
  year={2008}
}

@inproceedings{GI11a,
 author = {Georgiana Ifrim and Carsten Wiuf},
 title = {Bounded Coordinate-Descent for Biological Sequence
Classification in High Dimensional Predictor Space},
 booktitle = {Proceedings of the 17th ACM SIGKDD International
Conference on Knowledge Discovery and Data Mining},
 year = {2011}
}

@Manual{I12a,
  title = 	 {Intel Math Kernel Library Reference Manual},
  OPTkey = 	 {},
  author =	 {Intel},
  organization = {},
  OPTaddress = 	 {},
  OPTedition = 	 {},
  OPTmonth = 	 {},
  OPTyear = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@inproceedings{SI15a,
  title={Batch normalization: accelerating deep network training by reducing internal covariate shift},
  author={Ioffe, Sergey and Szegedy, Christian},
  booktitle={Proceedings of the 32nd International Conference on Machine Learning (ICML)},
  pages={448--456},
  year={2015}
}

@InProceedings{MI07a,
  author = 	 {Michael Isard and Mihai Budiu and Yuan Yu and Andrew Birrell and Dennis Fetterly},
  title = 	 {Dryad: distributed data-parallel programs from sequential building blocks},
  OPTcrossref =  {},
  OPTkey = 	 {},
  booktitle =	 {Proceedings of the second ACM SIGOPS/EuroSys European Conference on Computer Systems },
  pages =	 {59--72},
  year =	 {2007},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTaddress = 	 {},
  OPTmonth = 	 {},
  OPTorganization = {},
  OPTpublisher = {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@InProceedings{HI02a,
  title={Efficient support vector classifiers for named entity recognition},
  author={Isozaki, Hideki and Kazawa, Hideto},
  booktitle={Proceedings of COLING},
  pages={390--396},
  year={2002}
}

@article{AI03a,
  title={{An automatic metadata generation method for music retrieval-by-impression dealing with impression-transition.}},
  author={Ijichi, A. and Kiyoki, Y.},
  journal={Proc. the 7th IASTED International Conference on Internet and Multimedia Systems and Applications},
  pages={281--288},
  year={2003}
}

@InProceedings{JaaHau99b,
  author        = {Tommi S. Jaakkola and David Haussler},
  title         = {Probabilistic Kernel Regression Models},
  booktitle     = {Proceedings of the 1999 Conference on {AI} and
                  Statistics},
  year          = {1999},
  publisher={Society for Artificial Intelligence in Statistics}
} 

@Article{RAJ91a,
  author = 	 {R. A. Jacobs and M. I. Jordan and S. J. Nowlan and G. E. Hinton},
  title = 	 {Adaptive mixtures of local experts},
  journal = 	 {Neural Computation},
  year = 	 {1991},
  volume =	 {3},
  number =	 {1},
  pages =	 {79--87}
}

@inproceedings{AHJ19a,
  title={Unifying Explicit and Implicit Feedback for Rating Prediction and Ranking Recommendation Tasks},
  author={Jadidinejad, Amir H. and Macdonald, Craig and Ounis, Iadh},
  booktitle={Proceedings of the Fifth ACM SIGIR International Conference on Theory of Information Retrieval},
  pages={149--156},
  year={2019}
}

@incollection{MJ14a,
	title={Communication-efficient distributed dual coordinate ascent},
	author={Jaggi, Martin and Smith, Virginia and Tak{\'a}{\v{c}}, Martin and Terhorst, Jonathan and Hofmann, Thomas and Jordan, Michael I},
	booktitle = {Advances in Neural Information Processing Systems 27},
pages = {3068--3076},	
	year={2014}
}

@incollection{MJ14a-short,
	title={Communication-efficient distributed dual coordinate ascent},
	author={Jaggi, Martin and Smith, Virginia and Tak{\'a}{\v{c}}, Martin and Terhorst, Jonathan and Hofmann, Thomas and Jordan, Michael I},
	booktitle = {NIPS},
	year={2014}
}

@inproceedings{MJ12a,
author = {Jahrer, Machael and T\"{o}scher, Andreas and Lee, Jeong-Yoon and Deng, Jingjing and Zhang, Hang and Spoelstra, Jacob},
title = {Ensemble of Collaborative Filtering and Feature Engineered Model for Click Through Rate Prediction},
booktitle = {KDD Cup 2012 Workshop},
year = {2012},
}

@inproceedings{HJ16a,
author = {Jain, Himanshu and Prabhu, Yashoteja and Varma, Manik},
title = {Extreme Multi-Label Loss Functions for Recommendation, Tagging, Ranking \& Other Missing Label Applications},
year = {2016},
doi = {10.1145/2939672.2939756},
booktitle = {Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)},
pages = {935--944}
}

@inproceedings{HJ19a,
author = {Jain, Himanshu and Balasubramanian, Venkatesh and Chunduri, Bhanu and Varma, Manik},
title = {Slice: Scalable Linear Extreme Classifiers Trained on 100 Million Labels for Related Searches},
year = {2019},
booktitle = {Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining (WSDM)},
pages = {528--536}
}

@InProceedings{MJ10a,
  author  = {Jamali, Mohsen and Ester, Martin},
  title   = {A Matrix Factorization Technique with Trust Propagation
      for Recommendation in Social Networks},
  booktitle = {Proceedings of the Fourth ACM Conference on Recommender
      Systems},
  year    = {2010},
  pages   = {135--142}
}

@InProceedings{MJ10a-short,
  author  = {Jamali, Mohsen and Ester, Martin},
  title   = {A Matrix Factorization Technique with Trust Propagation
      for Recommendation in Social Networks},
  booktitle = {RecSys},
  year    = {2010}
}

@inproceedings{JS1961,
author      = {Willard D. James and Charles M. Stein},
booktitle   = {Proceedings of the Fourth Berkeley Symposium on Mathematical Statistics and Probability},
pages       = {361--379},
title       = {Estimation with quadratic loss},
volume      = {1},
year        = {1961}
}

@article{KJ02a,
 author = {J\"{a}rvelin, Kalervo and Kek\"{a}l\"{a}inen, Jaana},
 title = {Cumulated gain-based evaluation of {IR} techniques},
 journal = {ACM Transactions on Information Systems},
 year = {2002},
 volume = {20},
 number = {4},
 pages = {422--446}
}

@Article{FJ93a,
  author = 	 {F. Jarre},
  title = 	 {An interior-point method for minimizing and maximum 
eigenvalue of a linear combination of matrices},
  journal = 	 {SIAM J. Control Optim.},
  year = 	 {1993},
  volume =	 {31},
  pages =	 {1360--1377}
}

@inproceedings{KJ16a,
  title={Extreme {F}-measure maximization using sparse probability estimates},
  author={Jasinska, Kalina and Dembczy\'nski, Krzysztof and Busa-Fekete, R{\'o}bert and Pfannschmidt, Karlson and Klerx, Timo and H\"ullermeier, Eyke},
  booktitle={Proceedings of The 33rd International Conference on Machine Learning (ICML)},
  pages={1435--1444},
  year={2016}
}

@misc{KJK20a,
      title={Probabilistic Label Trees for Extreme Multi-label Classification},
      author={Kalina Jasinska-Kobus and Marek Wydmuch and Krzysztof Dembczynski and Mikhail Kuznetsov and Robert Busa-Fekete},
      year={2020},
      eprint={2009.11218},
      archivePrefix={arXiv},
      primaryClass={cs.LG}
}

@inproceedings{GJ10a,
  title={Comparison of implicit and explicit feedback from an online music recommendation service},
  author={Jawaheer, Gawesh and Szomszor, Martin and Kostkova, Patty},
  booktitle={Proceedings of the 1st international workshop on information heterogeneity and fusion in recommender systems},
  pages={47--51},
  year={2010}
}

@Article{ETJ57a,
   author = 	 {Edwin T. Jaynes},
   title = 	 {Information Theory and Statistical Mechanics},
   journal = 	 {Physical Review},
   year = 	 {1957},
   OPTkey = 	 {},
   volume =	 {106},
   number =	 {4},
   pages =	 {620--630},
   OPTmonth = 	 {May},
   OPTnote = 	 {},
   OPTannote = 	 {}
}

@Article{ETJ57b,
   author = 	 {Edwin T. Jaynes},
   title = 	 {Information Theory and Statistical Mechanics II},
   journal = 	 {Physical Review},
   year = 	 {1957},
   OPTkey = 	 {},
   volume =	 {108},
   number =	 {2},
   pages =	 {171--190},
   OPTmonth = 	 {October},
   OPTnote = 	 {},
   OPTannote = 	 {}
}


@article{AJ77,
author      = {A. Jennings and G. M. Malik},
journal     = {J. Inst. Maths. Appl.},
pages       = {307--316},
title       = {Partial elimination},
volume      = {20},
year        = {1977}
}

@inproceedings{OJ20a,
  title={Joint Policy-Value Learning for Recommendation},
  author={Jeunen, Olivier and Rohde, David and Vasile, Flavian and Bompaire, Martin},
  booktitle={Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)},
  pages={1223--1233},
  year={2020}
}

@inproceedings{SJ20a,
    title = "Dilated Convolutional Attention Network for Medical Code Assignment from Clinical Text",
    author = "Ji, Shaoxiong  and
      Cambria, Erik  and
      Marttinen, Pekka",
    booktitle = "Proceedings of the Third Clinical Natural Language Processing Workshop",
    year = "2020",
    doi = "10.18653/v1/2020.clinicalnlp-1.8",
    pages = "73--78",
}

@misc{SJ21a,
      title={Medical Code Assignment with Gated Convolution and Note-Code Interaction}, 
      author={Shaoxiong Ji and Shirui Pan and Pekka Marttinen},
      year={2021},
      url={https://arxiv.org/abs/2010.06975},
      note={arXiv preprint arXiv:2010.06975}
}

@article{SJ21b,
  title={Does the magic of {BERT} apply to medical code assignment? A quantitative study},
  author={Ji, Shaoxiong and H{\"o}ltt{\"a}, Matti and Marttinen, Pekka},
  journal={Computers in Biology and Medicine},
  volume={139},
  pages={104998},
  year={2021}
}

@article{HJ96a,
  title={Globally and superlinearly convergent trust-region algorithm for convex {SC} 1-minimization problems and its application to stochastic programs},
  author={Jiang, H. and Qi, L.},
  journal={Journal of Optimization Theory and Applications},
  volume={90},
  number={3},
  pages={649--669},
  year={1996},
  publisher={Springer}
}

@inproceedings{TJ21a,
  title={Light{XML}: Transformer with dynamic negative sampling for high-performance extreme multi-label text classification},
  author={Jiang, Ting and Wang, Deqing and Sun, Leilei and Yang, Huayi and Zhao, Zhengyang and Zhuang, Fuzhen},
  booktitle={Proceedings of the AAAI conference on artificial intelligence},
  volume={35},
  number={9},
  pages={7987--7994},
  year={2021}
}

@inproceedings{RJ03a,
  title={A faster iterative scaling algorithm for conditional exponential model},
  author={Jin, Rong and Yan, Rong and Zhang, Jian and Hauptmann, Alex G.},
  booktitle = {Proceedings of the Twentieth International Conference on
               Machine Learning (ICML)},
  year      = {2003},
  pages     = {282--289}
}

@inproceedings{RJ03a-short,
  title={A faster iterative scaling algorithm for conditional exponential model},
  author={Jin, R. and Yan, R. and Zhang, J. and Hauptmann, A.G.},
  booktitle = {ICML},
  year      = {2003},
  pages     = {}
}

@article{YJ08a,
  title={Visualrank: Applying pagerank to large-scale image search},
  author={Jing, Yushi and Baluja, Shumeet},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  volume={30},
  number={11},
  pages={1877--1890},
  year={2008}
}

@article{YJ08a-short,
  title={Visualrank: Applying pagerank to large-scale image search},
  author={Jing, Yushi and Baluja, Shumeet},
  journal = {IEEE PAMI},  
  volume={30},
  pages={1877--1890},
  year={2008}
}

@article{KJ19a,
    title={Search Property of Nonlinear Map Optimization},
    author={Kenya Jin'no and Tomoyuki Sasaki and Hidehiro Nakano},
    journal={IEEE Congress on Evolutionary Computation},
    year={2019},
    pages={3213-3220}
}

@InProceedings{TJ98a,
  author = 	 "Thorsten Joachims",
  title = 	 "Making large-scale {SVM} learning practical",
  chapter = 	 "11",
  year =	 "1998",
  editor = 	 {Bernhard Sch\"{o}lkopf and Christopher J. 
		  C. Burges and Alexander J. Smola},
  booktitle = 	 "Advances in Kernel Methods -- Support 
		  Vector Learning",
  pages ={169--184},
  publisher = 	 "MIT Press",
  address =	 "Cambridge, MA"
}


@InProceedings{TJ98a-short,
  author =   "Thorsten Joachims",
  title =    "Making large-scale {SVM} learning practical",
  chapter =    "11",
  year =   "1998",
  booktitle =    "Advances in Kernel Methods - Support
      Vector Learning",
  publisher =    "MIT Press"
} 


@inproceedings{TJ98b,
    author = "Thorsten Joachims",
    title = "Text categorization with support vector machines: learning
with many relevant features",
    booktitle = "Proceedings of {ECML}-98, 10th European Conference on
Machine Learning",
    number = "1398",
    publisher = "Springer Verlag, Heidelberg, DE",
    address = "Chemnitz, DE",
    editor = "Claire N{\'{e}}dellec and C{\'{e}}line Rouveirol",
    pages = "137--142",
    year = "1998",
    url = "citeseer.ist.psu.edu/joachims97text.html" 
}


@inproceedings{TJ98b-short,
    author = "Thorsten Joachims",
    title = "Text categorization with support vector machines: learning
with many relevant features",
    booktitle = "ECML",
    pages = "137--142",
    year = "1998"
}


@InProceedings{TJ99a,
  author = 	 {Thorsten  Joachims},
  title = 	 {Transductive inference for text classification using support vector machines},
  booktitle = 	 {Proceedings of International Conference on Machine Learning},
  year =	 {1999}
}

@Misc{TJ00a,
  author =	 {Thorsten  Joachims},
  year = {2000},
  note =	 {Private communication}
}

@InProceedings{Joachims00b,
  author        = {T. Joachims},
  title         = {Estimating the Generalization Performance of a {SVM}
                  Efficiently},
  booktitle     = {Proceedings of the International Conference on Machine
                  Learning},
  publisher     = {Morgan Kaufman},
  address       = {San Francisco},
  url           = {http://www-ai.cs.uni-dortmund.de/DOKUMENTE/joachims_00a.ps.gz},
  year          = {2000}
}


 @PhdThesis{TJ00c,
  author = 	 {Thorsten Joachims},
  title = 	 {The Maximum-Margin Approach to Learning Text Classifiers: Methods, Theory, and Algorithms},
  school = 	 {Universitaet Dortmund},
  year = 	 {2000}
}

@conference{TJ02a,
  title={Optimizing search engines using clickthrough data},
  author={Joachims, Thorsten},
  booktitle={Proceedings of the Eighth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining},
  year={2002}
}

@conference{TJ02a-short,
  title={Optimizing search engines using clickthrough data},
  author={Joachims, Thorsten},
  booktitle={ACM KDD},
  year={2002}
}

@InProceedings{TJ05a,
author = {Thorsten Joachims},
title = {A Support Vector Method for Multivariate Performance Measures},
booktitle = {Proceedings of the Twenty Second International Conference on Machine
Learning (ICML)},
year = {2005}
}

@inproceedings{TJ05b,
  title = {Accurately interpreting clickthrough data as implicit feedback},
  author = {Joachims, Thorsten and Granka, Laura A and Pan, Bing and Hembrooke, Helene and Gay, Geri},
 booktitle = {Proceedings of the 28th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)},
  pages = {154--161},
  year = {2005}
}

@inproceedings{TJ05b-short,
  title = {Accurately interpreting clickthrough data as implicit feedback},
  author = {Joachims, Thorsten and Granka, Laura A and Pan, Bing and Hembrooke, Helene and Gay, Geri},
 booktitle = {SIGIR},
  year = {2005}
}

@InProceedings{TJ06a,
   author = 	 {Thorsten Joachims},
   title = 	 {Training Linear {SVM}s in Linear Time},
   booktitle = 	 {Proceedings of the Twelfth ACM SIGKDD International  
Conference on Knowledge Discovery and Data Mining},
   OPTcrossref =  {},
   OPTkey = 	 {},
   OPTpages = 	 {},
   year =	 {2006},
   OPTeditor = 	 {},
   OPTvolume = 	 {},
   OPTnumber = 	 {},
   OPTseries = 	 {},
   OPTaddress = 	 {},
   OPTmonth = 	 {},
   OPTorganization = {},
   OPTnote = 	 {},
   OPTannote = 	 {}
}

@InProceedings{TJ06a-short,
  author = 	 {T. Joachims},
  title = 	 {Training Linear {SVM}s in Linear Time},
  booktitle = 	 {KDD},
  year =	 {2006},
  OPTannote = 	 {}
}

@article{TJ08a,
author      = {Thorsten Joachims and Thomas Finley and Chun-Nam John Yu},
journal     = {Machine Learning Journal},
title       = {Cutting-Plane training of structural {SVM}s},
volume = {77},
number = {1},
year = {2009},
pages = {27--59}
}
% note        = {{Multi-class} code available at {\tt http://svmlight.joachims.org/svm\_multiclass.html}},

@article{TJ08a-short,
author      = {Thorsten Joachims and Thomas Finley and Chun-Nam John Yu},
journal     = {Machine Learning},
title       = {Cutting Plane training of structural {SVM}s},
volume = {77},
year = {2009}
}
% note        = {{Multi-class} code available at {\tt http://svmlight.joachims.org/svm\_multiclass.html}},

@inproceedings{TJ17a,
title={Unbiased learning-to-rank with biased feedback},
author={Joachims, Thorsten and Swaminathan, Adith and Schnabel, Tobias},
booktitle={Proceedings of the Tenth ACM International Conference on Web Search and Data Mining},
pages={781--789},
year={2017}
}

@inproceedings{TJ17a-short,
title={Unbiased learning-to-rank with biased feedback},
author={Joachims, Thorsten and Swaminathan, Adith and Schnabel, Tobias},
booktitle={WSDM},
year={2017}
}


@inproceedings{TJ18a,
title={Deep learning with logged bandit feedback},
author={Joachims, Thorsten and Swaminathan, Adith and de Rijke, Maarten},
booktitle = {Proceedings of the International Conference on Learning Representations (ICLR)},
year={2018}
}

@inproceedings{GHJ94a,
    author = {George H. John and Ron Kohavi and Karl Pfleger},
    title = {Irrelevant Features and the Subset Selection Problem},
    booktitle = {International Conference on Machine Learning},
    pages = {121--129},
    note = {Journal version in AIJ, available at http://citeseer.nj.nec.com/13663.html},
    year = {1994}
}

@Book{JJA95a,
  author =       {John, J.A. and Williams, E.R.},
  title =        {Cyclic and Computer Generated Designs},
  publisher =    {Chapman \& Hall},
  year =         {1995},
  edition =	 {Second},
  address =      {United Kingdom}
}

@Book{JJA95a-short,
  author =       {John, J.A. and Williams, E.R.},
  title =        {Cyclic and Computer Generated Designs},
  publisher =    {Chapman \& Hall},
  year =         {1995}
}

@article{AJ16a,
  title={{MIMIC-III}, a freely accessible critical care database},
  author={Johnson, Alistair E.W. and Pollard, Tom J. and Shen, Lu and Lehman, Li-Wei H. and Feng, Mengling and Ghassemi, Mohammad and Moody, Benjamin and Szolovits, Peter and Celi, Leo Anthony and Mark, Roger G.},
  journal={Scientific Data},
  volume={3},
  number={1},
  pages={1--9},
  year={2016},
  doi={10.1038/sdata.2016.35}
}

@article{AJ16a-short,
  title={{MIMIC-III}, a freely accessible critical care database},
  author={Johnson, Alistair E.W. and Pollard, Tom J. and Shen, Lu and Lehman, Li-Wei H. and Feng, Mengling and Ghassemi, Mohammad and Moody, Benjamin and Szolovits, Peter and Celi, Leo Anthony and Mark, Roger G.},
  journal={Scientific Data},
  year={2016}
}

@inproceedings{JMJ19a,
  title={Deep learning and thresholding with class-imbalanced big data},
  author={Johnson, Justin M. and Khoshgoftaar, Taghi M.},
  booktitle={Proceedings of the 18th IEEE International Conference on Machine Learning and Applications (ICMLA)},
  pages={755--762},
  year={2019}
}

@inproceedings{RJ13a,
	title={Accelerating stochastic gradient descent using predictive
		variance reduction},
	author={Johnson, Rie and Zhang, Tong},
	booktitle={Advances in Neural Information Processing
		Systems},
	pages={315--323},
	year={2013}
}

@inproceedings{JR15a,
    title = "Effective Use of Word Order for Text Categorization with Convolutional Neural Networks",
    author = "Johnson, Rie  and
      Zhang, Tong",
    booktitle = "Proceedings of the 2015 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies",
    year = "2015"
}

@article{KJ72a,
    author = {Karen S. Jones},
    journal = {Journal of Documentation},
    number = {1},
    pages = {11--20},
    publisher = {Taylor Graham Publishing},
    title = {{A statistical interpretation of term specificity and its application in retrieval}},
    volume = {28},
    year = {1972}
}

@article{KJ72a-short,
    author = {Karen S. Jones},
    journal = {Journal of Documentation},
    title = {{A statistical interpretation of term specificity and its application in retrieval}},
    year = {1972}
}

@article{MTJ91,
author      = {M. T. Jones and P. E. Plassmann},
title       = {An improved incomplete {C}holesky factorization},
journal     = {ACM Trans. Math. Software},
pages       = {5--17},
volume      = {21},
year        = {1995}
}

@MastersThesis{YCJ14a,
  author = {Yu-Chin Juan},
  title =  {A Fast Parallel Stochastic Gradient Method for Matrix Factorization in Shared Memory Systems},
  school = {Department of Computer Science and Information Engineering, National Taiwan University},
  year = {2014},
  month ={Jan},
}

@InProceedings{YJ16a,
  author={Yuchin Juan and Yong Zhuang and Wei-Sheng Chin and  Chih-Jen Lin},
  title = 	 {Field-aware factorization machines for {CTR} Prediction},
  OPTcrossref =  {},
  OPTkey = 	 {},
  booktitle={Proceedings of the ACM Recommender Systems Conference (RecSys)},
  year =	 {2016},
  url={http://www.csie.ntu.edu.tw/~cjlin/papers/ffm.pdf},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTpages = 	 {},
  OPTmonth = 	 {},
  OPTaddress = 	 {},
  OPTorganization = {},
  OPTpublisher = {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@inproceedings{YJ16a-short,
	title={Field-aware Factorization Machines for {CTR} Prediction},
	author={Juan, Yuchin and Zhuang, Yong and Chin, Wei-Sheng and
		Lin, Chih-Jen},
	booktitle={RecSys},
	year={2016}
}

@inproceedings{YJ17a,
  title={Field-aware factorization machines in a real-world online advertising system},
  author={Juan, Yuchin and Lefortier, Damien and Chapelle, Olivier},
  booktitle={Proceedings of the 26th International Conference on World Wide Web Companion},
  pages={680--688},
  year={2017}
}

@inproceedings{YJ17a-short,
  author={Juan, Yuchin and Lefortier, Damien and Chapelle, Olivier},
  title={Field-aware factorization machines in a real-world online advertising system},
  booktitle={WWW},
  year={2017}
}

@article{JHJ08a,
author      = {Jin Hyuk Jung and Dianne P. O'Leary and Andr\'e L. Tits},
title       = {Adaptive Constraint Reduction for Training Support  
Vector Machines},
journal     = {Electronic Transactions on Numerical Analysis},
volume      = {31},
pages       = {156--177},
year        = {2008}
}


@TechReport{MJ96,
author      = {M. J\"{u}nger and V. Kaibel},
address     = {Koln, Pohligstr. 1, 50969 Koln},
institution = {Institut f\"{u}r Informatik, Universit\"{a}t zu K\"{o}ln},
title       = {A basic study of the {QAP}-polytope},
year        = {1996}
}

@BOOK{DJ08a,
  author = {Daniel Jurafsky and James H. Martin},
  title = {Speech and Language Processing: An Introduction 
to Natural Language Processing, Computational Linguistics 
and Speech Recognition},
  publisher = {Prentice Hall},
  edition =	 {second},
  year = {2008}
}


@misc{MK14a,
  author    = {Mojtaba Kadkhodaie and Maziar Sanjabi and Zhi-Quan Luo},
  title     = {On the Linear Convergence of the Approximate Proximal Splitting Method for Non-Smooth Convex Optimization},
  year      = {2014},
  note={arXiv preprint arXiv:1404.5350}
}

@inproceedings{RK17a,
author = "Kadlec, Rudolf and Bajgar, Ondrej and Kleindienst, Jan",
editor = "Blunsom, Phil and Bordes, Antoine and Cho, Kyunghyun and Cohen, Shay and Dyer, Chris and Grefenstette, Edward and Hermann, Karl Moritz and Rimell, Laura and Weston, Jason and Yih, Scott",
title = "Knowledge Base Completion: Baselines Strike Back",
booktitle = "Proceedings of the Second Workshop on Representation Learning for {NLP}",
year = "2017",
doi = "10.18653/v1/W17-2609",
pages = "69--74",
}

@Article{KC02a,
  author = 	 {Wei-Chun Kao and Kai-Min Chung and Chia-Liang Sun and  Chih-Jen Lin},
  title = 	 {Decomposition Methods for Linear Support Vector Machines},
 journal     ={Neural Computation},
 pages={1689--1704},
 volume={16},
number={8},
  year =	 {2004},
  url={http://www.csie.ntu.edu.tw/~cjlin/papers/linear.pdf}
}

@Article{KC02a-short,
  author = 	 {Wei-Chun Kao and Kai-Min Chung and Chia-Liang Sun and  Chih-Jen Lin},
  title = 	 {Decomposition Methods for Linear Support Vector Machines},
 journal     ={Neural Comput.},
 pages={1689--1704},
 volume={16},
number={8},
  year =	 {2004}
}




@InProceedings{PK12a,
  author = 	 {Purushottam Kar and Harish Karnick},
  title = 	 {Random Feature Maps for Dot Product Kernels},
  OPTcrossref =  {},
  OPTkey = 	 {},
  booktitle =	 {Proceedings of the 15th International Conference on Artificial Intelligence and Statistics (AISTATS)},
  year =	 {2012},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  pages =	 {583--591},
  OPTseries = 	 {},
  OPTaddress = 	 {},
  OPTmonth = 	 {},
  OPTorganization = {},
  OPTpublisher = {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@Article{AK91a,
  author = 	 {Aram Karali{\u c} and and Vladimir Pirnat},
  title = 	 {Significance level based multiple tree classification},
  journal = 	 {Informatica},
  year = 	 {1991},
  OPTkey = 	 {},
  volume =	 {15},
  number =	 {5},
  OPTpages = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@article{MK10a,
	title={Multiple incremental decremental learning of support vector machines},
	author={Karasuyama, Masayuki and Takeuchi, Ichiro},
	journal={IEEE Transactions on Neural Networks},
	volume={21},
	number={7},
	pages={1048--1059},
	year={2010}
}

@article{MK10a-short,
	title={Multiple incremental decremental learning of support vector machines},
	author={Karasuyama, Masayuki and Takeuchi, Ichiro},
	journal={IEEE TNN},
	volume={21},
	pages={1048--1059},
	year={2010}
}

@inproceedings{HK16a,
	title = {Linear Convergence of Gradient and Proximal-Gradient
		Methods under {P}olyak-{\L}ojasiewicz Condition},
	author = {Karimi, Hamed and Nutini, Julie and  Schmidt, Mark},
	year = {2016},
	booktitle = {Joint European Conference on Machine Learning and
		Knowledge Discovery in Databases}
}
@inproceedings{HK16a-short,
	title = {Linear Convergence of Gradient and Proximal-Gradient
		Methods under {P}olyak-{\L}ojasiewicz Condition},
	author = {Karimi, Hamed and Nutini, Julie and  Schmidt, Mark},
	year = {2016},
	booktitle = {ECML/PKDD}
}

@PhdThesis{SEK95a,
  author = 	 {S. E. Karisch},
  title = 	 {Nonlinear approaches for the quadratic assignment
                  and graph partition problems},
  school = 	 {Graz University of Technology},
  year = 	 {1995},
  address =	 {Graz, Austria}
}


@article{SEK95b,
author = {S. E. Karisch and F. Rendl},
title = {Lower bounds for the quadratic assignment problem via triangle
 decompositions},
journal= {Math. Programming},
 volume={71(2)},
 pages ={137--152},
  year={1995}  
}


@InProceedings{LK98a,
  author = 	 "Linda Kaufman",
  title = 	 "Solving the quadratic programming problem arising in 
		  support vector classification",
  chapter = 	 "10",
  year		= {1999},
  editor = 	 {Bernhard Sch\"{o}lkopf and Christopher J. 
		  C. Burges and Alexander J. Smola},
  booktitle = 	 "Advances in Kernel Methods - Support 
		  Vector Learning",
  publisher = 	 "MIT Press",
  address =	 "Cambridge, MA"
}


@article{kass95,
author      = {Robert E. Kass and Adrian E. Raftery},
title       = {Bayes factors},
journal     = {Journal of the American Statistical Association}, 
volume      = {90},
number      = {430},
pages       = {773--795},
year        = {1995}
}

@inproceedings{JK03a,
        author = {Jun'ichi Kazama and Jun'ichi Tsujii},
        title = {Evaluation and extension of maximum entropy models
with inequality constraints},
        booktitle = {Proceedings of the Conference on Empirical Methods in
Natural Language Processing},
        year = {2003},
        pages = {137--144}
  }

 
@inproceedings{JK03a-short,
  author = {Jun'ichi Kazama and Jun'ichi Tsujii},
  title = {Evaluation and extension of maximum entropy models with 
inequality constraints},
  booktitle = {EMNLP},
  year = {2003}
  }

@incollection{HK05a,
 author = {Hideto {Kazawa} and Tomonori {Izumitani} and Hirotoshi {Taira}
and Eisaku {Maeda}},
 title = {Maximal Margin Labeling for Multi-Topic Text Categorization},
 booktitle = {Advances in Neural Information Processing Systems 17},
 editor = {Lawrence K. Saul and Yair Weiss and {L\'{e}on} Bottou},
 publisher = {MIT Press},
 address = {Cambridge, MA},
 pages = {649--656},
 year = {2005},
 original = "0649_238.PDF"
}

@incollection{HK05a-short,
 author = {Hideto {Kazawa} and Tomonori {Izumitani} and Hirotoshi {Taira}
and Eisaku {Maeda}},
 title = {Maximal Margin Labeling for Multi-Topic Text Categorization},
 booktitle = {{NIPS} 17},
 pages = {649--656},
 year = {2005}
}

@inproceedings{BCK23a,
author = {Ke, Bo-Cheng and Li, Min-Han and Chen, Yu and Cheng, Chia-Yu and Chang, Chiao-Ju and Li, Yun-Fang and Wang, Shun-Yu and Fang, Chiao and Chen, Mike Y.},
title = {TurnAhead: Designing 3-DoF Rotational Haptic Cues to Improve First-Person Viewing (FPV) Experiences},
year = {2023},
isbn = {9781450394215},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3544548.3581443},
doi = {10.1145/3544548.3581443},
abstract = {First-Person View (FPV) drone is a recently developed category of drones designed for precision flying and for capturing exhilarating experiences that could not be captured before, such as navigating through tight indoor spaces and flying extremely close to subjects of interest. FPV viewing experiences, while exhilarating, typically have frequent rotations that can lead to visually induced discomfort. We present TurnAhead, which uses 3-DoF rotational haptic cues that correspond to camera rotations to improve the comfort, immersion, and enjoyment of FPV experiences. It uses headset-mounted air jets to provide ungrounded rotational forces and is the first device to support rotation around all 3 axes: yaw, pitch, and roll. We conducted a series of perception and formative studies to explore the design space of timing and intensity of haptic cues, followed by user experience evaluation, for a combined total of 44 participants (n=12, 8, 6, 18). Results showed that TurnAhead significantly improved overall comfort, immersion, and enjoyment, and was preferred by 89\% of participants.},
booktitle = {Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems},
articleno = {401},
numpages = {15},
keywords = {User Experience Design, First-person Viewing Video, Virtual Reality, Haptic Device},
location = {Hamburg, Germany},
series = {CHI '23}
}

		  

@InProceedings{SSK92a,
  author = 	 {S. S. Keerthi and N. K. Sancheti and A. Dattasharma},
  title = 	 {Transversality theorem: 
A useful tool for establishing genericity},
  booktitle = 	 {Proceedings of IEEE Conference on Decision and Control},
  year =	 {1992},
  address =	 {Tucson}
}

@TechReport{SSK99b,
  author = 	 {S. S. Keerthi and S. K. Shevade, C. Bhattacharyya and K. R. K. Murthy},
  title = 	 {A fast iterative nearest point algorithm for support vector machine classifier design},
  institution =  {Department of Computer Science and Automation, Indian Institute of Science},
  year = 	 {1999},
  number =	 {TR-ISL-99-03},
  address =	 {Bangalore, India}
}

@Article{SSK99c,
  author = 	 {S. Sathiya Keerthi and
 Shirish Krishnaj Shevade and Chiranjib Bhattacharyya and Karuturi Radha Krishna Murthy},
  title = 	 {Improvements to {SMO}
     Algorithm for {SVM} Regression},
  journal= {IEEE Transactions on Neural Networks},
  volume = {11},
  number =	 {5},
  pages       = {1188--1193},
  year = 	 {2000}
}


@Article{SSK99c-short,
  author = 	 {S. Sathiya Keerthi and
 Shirish Krishnaj Shevade and Chiranjib Bhattacharyya and Karuturi Radha Krishna Murthy},
  title = 	 {Improvements to {SMO}
     Algorithm for {SVM} Regression},
  journal= {IEEE TNN},
  volume = {11},
  pages       = {1188--1193},
  year = 	 {2000}
}


@Article{SSK00a,
  author = 	 {S. S. Keerthi and E. G. Gilbert},
  title = 	 {Convergence of a generalized {SMO} algorithm for {SVM} classifier
                      design},
  year = 	 {2002},
  journal = {Machine Learning},
  volume={46},
  pages={351--360}
}


@Article{SSK00b,
  author = 	 {S. S. Keerthi and S. K. Shevade and  C. Bhattacharyya and K. R. K. Murthy},
  title = 	 {A fast iterative nearest point algorithm for support vector machine classifier design},
  journal = 	 {IEEE Transactions on  Neural Networks},  
  year = 	 {2000},
  volume =       {11},
  number =	 {1},
  pages       = {124--136}
}



@TechReport{SSK00c,
  author = 	 {S.  Sathiya Keerthi and Chong Jin Ong and Martin
M.S. Lee},
  title = 	 {Two Efficient Methods for Computing Leave-One-Out
Error in SVM Algorithms},
  institution =  {Department of Mechanical and Production Engineering, National University of Singapore
},
  year = 	 {2000},
  address =	 {Singapore}
}



@TechReport{SSK00d,
  author = 	 {S.  Sathiya   Keerthi and Chong Jin   Ong},
  title = 	 {On the role of the threshold parameter in {SVM} training algorithms},
  institution =  {Department of Mechanical and Production Engineering, National University of Singapore
},
  year = 	 {2000},
  address =	 {Singapore},
  number =	 {CD-00-09}, 
  url = {http://guppy.mpe.nus.edu.sg/~mpessk/papers/decomp.ps.gz}
}

@Article{SSK01a,
  author = 	 {S. Sathiya Keerthi and
 Shirish Krishnaj Shevade and Chiranjib Bhattacharyya and Karuturi Radha Krishna Murthy},
  title = 	 {Improvements to {P}latt's {SMO}
     Algorithm for {SVM} Classifier Design},
  year = 	 {2001},
  journal = {Neural Computation},
  volume = {13},
   issue     = {3},
pages       = {637--649}
}

@Article{SSK01a-short,
  author = 	 {S. Sathiya Keerthi and
 Shirish Krishnaj Shevade and Chiranjib Bhattacharyya and Karuturi Radha Krishna Murthy},
  title = 	 {Improvements to {P}latt's {SMO}
     Algorithm for {SVM} Classifier Design},
  year = 	 {2001},
  journal = {Neural Comput.},
  volume = {13},
   issue     = {3},
pages       = {637--649}
}


@Article{SSK01b,
  author = 	 {S. Sathiya Keerthi},
  title = 	 {Efficient Tuning of {SVM} Hyperparameters Using
Radius/Margin Bound and Iterative Algorithms
},
  year = 	 {2002},
  journal={IEEE Transactions on  Neural Networks},
  volume={13},
  pages={1225--1229}
}




@TechReport{SSK02a,
  author = 	 {S. Sathiya Keerthi},
  title = 	 {When $\sigma \rightarrow \infty$, {SVM} with Gaussian kernel is the 
same as {SVM} with linear kernel},
  institution =  {Department of Mechanical and Production Engineering, National University of Singapore
},
  year = 	 {2002},
  address =	 {Singapore}
}




@Article{SSK02b,
  author =       {S. Sathiya Keerthi and Chih-Jen Lin},
  title =        {Asymptotic Behaviors of Support Vector Machines with
                  {G}aussian Kernel},
  journal =      {Neural Computation},
  volume =       {15},
  number =       {7},
  pages =        {1667--1689},
  year =         {2003}
}

@Article{SSK02b-short,
  author =       {S. Sathiya Keerthi and Chih-Jen Lin},
  title =        {Asymptotic Behaviors of Support Vector Machines with
                  {G}aussian Kernel},
  journal =      {Neural Comput.},
  volume =       {15},
  number =       {7},
  pages =        {1667--1689},
  year =         {2003}
}


@Article{SSK03a,
 author    = {S. Sathiya Keerthi and Kaibo Duan and Shirish Shevade and Aun Neow Poo},
  title =        {A fast dual algorithm for kernel logistic regression},
 journal   = {Machine Learning},
 year      = {2005},
 pages     = {151--165},
 volume    = {61}
}

@article{SSK05a,
  title={A Modified Finite {N}ewton Method for Fast Solution of Large Scale Linear {SVM}s},
  author={Keerthi, S. Sathiya  and DeCoste, Dennis},
  journal={Journal of Machine Learning Research},
  volume={6},
  pages={341--361},
  year={2005},
  publisher={MIT Press Cambridge, MA, USA}
}


@article{SSK05a-short,
  title={A Modified Finite {N}ewton Method for Fast Solution of Large Scale Linear {SVM}s},
  author={Keerthi, S. Sathiya  and DeCoste, Dennis},
  journal={JMLR},
  volume={6},
  pages={341--361},
  year={2005}
}


@Article{SSK06a,
  author = 	 {S. Sathiya Keerthi and Olivier Chapelle and Dennis DeCoste},
  title = 	 {Building Support Vector Machines with Reduced Classifier Complexity},
  journal = {Journal of Machine Learning Research},
  year = 	 {2006},
  OPTkey = 	 {},
  volume =	 {7},
  OPTnumber = 	 {},
  pages =	 {1493--1515},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@article{SSK07a,
  title={A fast tracking algorithm for generalized {LARS}/{LASSO}},
  author={Keerthi, S. Sathiya and Shevade, Shrish},
  journal={IEEE Transactions on Neural Networks},
  volume={18},
  number={6},
  pages={1826--1830},
  year={2007}
}

@inproceedings{SSK08a,
  author    = {S. Sathiya Keerthi and Sellamanickam Sundararajan and Kai-Wei Chang and Cho-Jui Hsieh and Chih-Jen Lin},
  title     = {A Sequential Dual Method for Large Scale Multi-Class Linear {SVM}s},
  booktitle = {Proceedings of the Forteenth ACM SIGKDD International
Conference on Knowledge Discovery and Data Mining},
  year      = {2008},
  pages     = {408--416},
  url={http://www.csie.ntu.edu.tw/~cjlin/papers/sdm_kdd.pdf}
} 

@inproceedings{SSK08a-short,
 author    = {S. S. Keerthi and S. Sundararajan and
K.-W. Chang and C.-J. Hsieh and C.-J. Lin},
 title     = {A Sequential Dual Method for Large Scale Multi-Class
Linear {SVM}s},
 booktitle = {KDD},
 year      = {2008}
}

@article{AK97a,
 author      ="Kehagias, Athanasios and Petridis, Vassilios",
 title       ="Time-Series Segmentation Using Predictive Modular 
               Neural Networks",
 pages       ="1691--1709",
 volume      ="9",
 parallelIssues="defined",
 journal     ="Neural Computation",
 year        ="1997",
 scope       ="learn",
 abstractURL ="http://skiron.control.ee.auth.gr/~kehagias/THN/97ckepe.htm",
 documentURL ="http://skiron.control.ee.auth.gr/~kehagias/THN/97ckepetx.ps.Z",
 keywords    ="multiple models, time series, classification, 
               segmentation, Bayesian"
}

@article{JEK60a,
  author = {Kelley, Jr, James E.},
  title = {The Cutting-plane Method for Solving Convex Programs},
  journal = {Journal of the Society for Industrial and Applied Mathematics},
  year = {1960}
}

@incollection{JK95a,
author={James Kennedy and Russell Eberhart},
booktitle={Proceedings of International Conference on Neural Networks (ICNN)},
title={Particle swarm optimization},
year={1995},
pages={1942-1948}
}

@article{DSK78,
author      = {D. S. Kershaw},
journal     = {J. Comp. Phys.},
pages       = {43--65},
title       = {The incomplete {C}holesky-conjugate gradient method for
                  the iterative solution of system of linear equations},
volume      = {26},
year        = {1978}
}

@article{NSK16a,
  title={A Second-order Method for Convex {L}1-regularized Optimization with Active-set Prediction},
  author={Keskar, Nitish Shirish and Nocedal, Jorge and {\"O}ztoprak, Figen and Waechter, Andreas},
  journal={Optimization Methods and Software},
  volume={31},
  number={3},
  pages={605--621},
  year={2016}
}

@article{SK20a,
  author    = {Sujay Khandagale and
               Han Xiao and
               Rohit Babbar},
  title     = {Bonsai: diverse and shallow trees for extreme multi-label classification},
  journal   = {Machine Learning},
  volume    = {109},
  pages     = {2099--2119},
  year      = {2020},
  doi       = {10.1007/s10994-020-05888-2}
}

@inproceedings{AK06a,
	author = {Anthony Khoo and Yuval Marom and David Albrecht},
	title = {Experiments with Sentence Classification},
	year = {2006},
	booktitle = {Australasian Language Technology Workshop}
}

@InProceedings{AK13a,
author = {Aditya Khosla and Raffay Hamid and Chih-Jen Lin and Neel Sundaresan},
title = {Large-Scale Video Summarization Using Web-Image Priors},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2013}
}

@InProceedings{MK20a,
author="Khosla, Megha and Leonhardt, Jurek and Nejdl, Wolfgang and Anand, Avishek",
title="Node Representation Learning for Directed Graphs",
booktitle="
Proceedings of the joint European Conference on Machine Learning and Knowledge Discovery in Databases (ECML/PKDD)",
year="2020",
pages="395--411",
}

@ARTICLE{MK21a,
author={Khosla, Megha and Setty, Vinay and Anand, Avishek},
journal={IEEE Transactions on Knowledge and Data Engineering},
title={A Comparative Study for Unsupervised Network Representation Learning},
year={2021},
volume={33},
number={5},
pages={1807-1818},
doi={10.1109/TKDE.2019.2951398}
}

@article{JK52a,
 author = {Kiefer, Jack and Wolfowitz, Jacob},
 title = {Stochastic Estimation of the Maximum of a Regression Function},
 journal = {The Annals of Mathematical Statistics},
 volume = {23},
 number = {3},
 pages = {462--466},
 year = {1952}
}

@article{JK52a-short,
 author = {Kiefer, Jack and Wolfowitz, Jacob},
 title = {Stochastic Estimation of the Maximum of a Regression Function},
 journal = {AMS},
 volume = {23},
 number = {3},
 year = {1952}
}

@inproceedings{JK19a,
    title = "{S}em{E}val-2019 Task 4: Hyperpartisan News Detection",
    author = "Kiesel, Johannes  and
      Mestre, Maria  and
      Shukla, Rishabh  and
      Vincent, Emmanuel  and
      Adineh, Payam  and
      Corney, David  and
      Stein, Benno  and
      Potthast, Martin",
    editor = "May, Jonathan  and
      Shutova, Ekaterina  and
      Herbelot, Aurelie  and
      Zhu, Xiaodan  and
      Apidianaki, Marianna  and
      Mohammad, Saif M.",
    booktitle = "Proceedings of the 13th International Workshop on Semantic Evaluation",
    year = "2019",
    doi = "10.18653/v1/S19-2145",
    pages = "829--839",
}

@article{DK08a,
    author = {Dongmin Kim and Suvrit Sra and Inderjit S. Dhillon},
    title = {Fast {N}ewton-type methods for the least squares nonnegative
matrix approximation problem},
    journal = {Statistical Analysis and Data Mining},
    year = {2008},
    pages = {38--51}
}

@article{HK08a,
    title={Non-negative matrix factorization based on alternating
non-negativity constrained least squares and active set method},
    author={Hyunsoo Kim and Haesun Park},
    journal={SIAM Journal on Matrix Analysis and Applications},
    volume={30},
    number={2},
    pages={713--730},
    year={2008}
}

@InProceedings{JK09b,
  title={Toward faster nonnegative matrix factorization: A new algorithm and
comparisons},
  author={Jingu Kim and Haesun Park},
  booktitle={Eighth IEEE International Conference on Data Mining},
  pages={353--362},
  year={2008},
  organization={IEEE}
}

@Article{JK08a,
  author =       {Jinseog Kim and Yuwon Kim and Yongdai Kim},
  title =        {A Gradient-Based Optimization Algorithm for {LASSO}},
  journal =      {Journal of Computational and Graphical Statistics},
  year =         {2008},
  volume =       {17},
  number =       {4},
  pages =        {994--1009}
}

@Article{KIK02a,
  author = 	 {Kwang In Kim and Keechul Jung and Se Hyun Park and Hang Joon Kim},
  title = 	 {Support vector machines for texture classification},
  journal = 	 {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = 	 {2002},
  volume =	 {24},
  number =	 {11},
  pages =	 {1542--1550}
}

@Article{SJK07a,
  author = {Seung-Jean Kim and Kwangmoo Koh and
Michael Lustig and Stephen Boyd and Dimitry
Gorinevsky},
  title = {An Interior Point Method for
Large-scale L1-regularized Least Squares},
  journal = {IEEE Journal on Selected Topics in
Signal Processing},
  year = {2007},
  pages = {606--617},
  volume = {1}
}
%   url = {http://www.stanford.edu/~boyd/papers/pdf/l1_ls.pdf},


@Article{SJK07a-short,
  author = {S.-J. Kim and K. Koh and M. Lustig and S. Boyd and
	  D. Gorinevsky},
  title = {An Interior Point Method for
Large-scale L1-regularized Least Squares},
  journal = {IEEE J-STSP},
  year = {2007},
  pages = {606--617},
  volume = {1}
}
%   url = {http://www.stanford.edu/~boyd/papers/pdf/l1_ls.pdf},


@inproceedings{YK04a,
  author    = {Yongdai Kim and Jinseog Kim},
  title     = {Gradient {LASSO} for feature selection},
  booktitle = {Proceedings of the 21st International Conference on
Machine Learning (ICML)},
  year      = {2004}
}

@inproceedings{YK14a,
    title = "Convolutional Neural Networks for Sentence Classification",
    author = "Kim, Yoon",
    booktitle = "Proceedings of the Conference on Empirical Methods in Natural Language Processing ({EMNLP})",
    year = "2014",
    doi = "10.3115/v1/D14-1181",
    pages = "1746--1751",
}

@inproceedings{YK14a-short,
    title = "Convolutional Neural Networks for Sentence Classification",
    author = "Kim, Yoon",
    booktitle = "EMNLP",
    year = "2014",
}

@article{GSK70a,
 author={Kimeldorf, George S. and Wahba, Grace},
 title={A Correspondence Between {B}ayesian Estimation on Stochastic Processes and Smoothing by Splines},
 journal={The Annals of Mathematical Statistics},
 volume={41},
 pages={495--502},
 year={1970}
}

@article{GSK70a-short,
 author={Kimeldorf, George S. and Wahba, Grace},
 title={A Correspondence Between {B}ayesian Estimation on Stochastic Processes and Smoothing by Splines},
 journal={Ann. Math. Stat.},
 volume={41},
 pages={495--502},
 year={1970}
}

@InProceedings{JK00a,
author = "J. Kindermann and E. Leopold and G. Paass",
title = "Multi-class Classification with Error Correcting Codes",
editor= "Leopold,Edda and Kirsten, Mathias",
booktitle = 	 {Treffen der GI-Fachgruppe 1.1.3, Maschinelles Lernen},
page="56--64",
note =	 {GMD Report 114},
year ="2000",
url = "http://citeseer.nj.nec.com/373131.html"
}

@article{DBK96a,
   title={Integrals and derivatives for correlated {G}aussian functions  
using matrix differential calculus},
   author={Kinghorn, Donald B.},
   journal={International Journal of Quantum Chemistry},
   volume={57},
   number={2},
   pages={141--155},
   year={1996}
}




@InProceedings{DPK15a,
  author = 	 {Diederik P. Kingma and Jimmy Ba},
  title = 	 {Adam: A Method for Stochastic Optimization},
  OPTcrossref =  {},
  OPTkey = 	 {},
  booktitle =	 {Proceedings of International Conference on Learning Representations (ICLR)},
  year =	 {2015},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTpages = 	 {},
  OPTmonth = 	 {},
  OPTaddress = 	 {},
  OPTorganization = {},
  OPTpublisher = {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@article{ki:op,
author      = {S. Kirkpatrick and Gelatt, Jr., C. D.  and M. P. Vecchi},
title       = {Optimization by simulated annealing},
journal     = {Science},
pages       = {671--680},
volume      = {220},
number      = {4598},
year        = {1983}
}

@article{JK97b,
  title =	{Exponentiated Gradient Versus Gradient Descent for Linear
Predictors},
  author =	{Jyrki Kivinen and Manfred K. Warmuth},
journal={Information and Computation},
  year = 	{1997},
volume={132},
 pages = {1--63}
}

@inproceedings{AK15a,
  title={Towards efficient Bayesian Optimization for Big Data},
  author={Klein, Aaron and Bartels, Simon and Falkner, Stefan and Hennig, Philipp and Hutter, Frank},
  booktitle={NIPS 2015 workshop on Bayesian Optimization (BayesOpt 2015)},
  year={2015}
}

@book{JK05a,
title = {Algorithm Design},
author = {Kleinberg, Jon and Tardos, Eva},
year = {2005},
isbn = {0321295358},
publisher = {Addison-Wesley Longman Publishing Co., Inc.}
}

@InProceedings{SK90a,
    author = "S. Knerr and L. Personnaz and G. Dreyfus",
    title = "Single-layer learning revisited: a stepwise procedure for building and
      training a neural network",
  booktitle = 	 {Neurocomputing: Algorithms, Architectures and Applications},
  editor =	 {J. Fogelman},
  publisher =	 {Springer-Verlag},
    year = "1990"
}

@InProceedings{SK90a-short,
    author = "S. Knerr and L. Personnaz and G. Dreyfus",
    title = "Single-layer learning revisited: a stepwise procedure for building and
      training a neural network",
  booktitle = 	 {Neurocomputing: Algorithms, Architectures and Applications},
    year = "1990"
}

@book{DEK73a,
  title={The Art of Computer Programming},
  author={Knuth, Donald E.},
  year={1973},
  volume={3},
  publisher={Addison-Wesley, Reading, MA}
}

@inproceedings{NK12a,
 author = {Koenigstein, Noam and Nice, Nir and Paquet, Ulrich and Schleyen, Nir},
 title = {The Xbox Recommender System},
 booktitle = {Proceedings of the Sixth ACM Conference on Recommender Systems},
 year = {2012},
 pages = {281--284}
} 

@inproceedings{NK12a-short,
 author = {Koenigstein, Noam and Nice, Nir and Paquet, Ulrich and Schleyen, Nir},
 title = {The Xbox Recommender System},
 booktitle = {RecSys},
 year = {2012}
} 

@inproceedings{NK13a,
  title={Xbox movies recommendations: Variational Bayes matrix factorization with embedded feature selection},
  author={Koenigstein, Noam and Paquet, Ulrich},
  booktitle={Proceedings of the 7th ACM Conference on Recommender Systems},
  pages={129--136},
  year={2013}
}

@inproceedings{NK13a-short,
  title={Xbox movies recommendations: Variational Bayes matrix factorization with embedded feature selection},
  author={Koenigstein, Noam and Paquet, Ulrich},
  booktitle={RecSys},
  year={2013}
}


@Inproceedings{SK09a,
author          = {Shimon Kogan and Dimitry Levin and Bryan R.
Routledge and Jacob S. Sagi and Noah A. Smith},
title           = {Predicting Risk from Financial Reports with
Regression},
booktitle       = {In Proceedings of the North American
Association for Computational Linguistics Human Language
Technologies Conference},
pages           = {272--280},
year            = {2009},
}


@Article{KK06a,
  author = 	 {Kwangmoo Koh and Seung-Jean Kim and Stephen Boyd },
  title = 	 {An interior-point method for large-scale L1-regularized logistic regression},
  journal = 	 {Journal of Machine Learning Research},
  year = 	 {2007},
  url = {http://www.stanford.edu/~boyd/l1_logistic_reg.html},
  OPTkey = 	 {},
  volume =	 {8},
  OPTnumber = 	 {},
  pages =	 {1519--1555},
  OPTmonth = 	 {},
  OPTannote = 	 {}
}

@Article{KK06a-short,
  author = 	 {Kwangmoo Koh and Seung-Jean Kim and Stephen Boyd},
  title = 	 {An interior-point method for large-scale L1-regularized logistic regression},
  journal = 	 {JMLR},
  year = 	 {2007},
  OPTkey = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTpages = 	 {},
  OPTmonth = 	 {},
  note =	 {To appear},
  OPTannote = 	 {}
}

@inproceedings{RK95a,
  title={A study of cross-validation and bootstrap for accuracy estimation and model selection},
  author={Kohavi, Ron},
  booktitle={International Joint Conference on Artificial Intelligence},
  volume={14},
  pages={1137--1145},
  year={1995}
}


@INPROCEEDINGS{RK95b,
	author = {Ron Kohavi and George H. John},
	title = {Automatic Parameter Selection by Minimizing Estimated Error},
	booktitle = {Proceedings of the Twelfth International Conference on Machine Learning (ICML)},
	year = {1995},
	pages = {304--312}
}

@INPROCEEDINGS{RK95b-short,
	author = {Ron Kohavi and George H. John},
	title = {Automatic Parameter Selection by Minimizing Estimated Error},
	booktitle = {ICML},
	year = {1995}
}


@InProceedings{JK97a,
author      = {Kohlmorgen, J. and  M{\"u}ller, K.-R. and  Pawelzik, K},
  booktitle = 	 {Proceedings of IEEE Neural Networks for Signal Processing Workshop},
pages       = {326--335},
title       = {Segmentation and Identification of Drifting Dynamical Systems },
year        = {1997}
}

@Inproceedings{JK00b,
author      = {Jens Kohlmorgen and  Steven Lemm and Gunna R{\"a}tsch and Klaus-Robert M{\"u}ller},
  booktitle = 	 {Proceedings of IEEE Neural Networks for Signal Processing Workshop},
pages       = {85--94},
title       = {Analysis of Nonstationary Time Series by Mixtures of Self-Organizing Predictors},
year        = {2000}
}

@article{JK00c,
author      = {Kohlmorgen, J. and  M{\"u}ller ,K.-R. and Rittweger, J. and Pawelzik, K},
journal     = {Biological Cybernetics },
pages       = {73--84},
title       = {Identification of Nonstationary Dynamics in Physiological Recordings },
volume      = {83},
year        = {2000}
}

@Article{RK97a,
  author = 	 {Ron Kohovi and George H. John},
  title = 	 {Wrappers for feature subset selection},
  journal =	 "Artificial Intellgence",
  year =	 "1997",
  volume =	 "97",
  number =	 "1--2",
  pages =	 "273--324"
}

@techreport {MK96a,
         author  = "M. Kojima and M. Shida and S. Shindoh",
         title   = "Local convergence of predictor-corrector
infeasible-interior-point algorithms for {SDP}s and {SDLCP}s",
         institution = "Dept. of Information Sciences",
         address = "Tokyo Institute of Technology, Tokyo, Japan",
         year    = "1996",
         note    = {To appear in {\em Math. Programming}}
     }


@Article{MK97a,
  journal = 	 {SIAM J. Optim.},
  year = 	 {1997},
  volume =	 {7},
  pages =	 {86--125},
  author = 	 {Masakazu Kojima and Susumu Shindoh and Shinji Hara},
  title = 	 {Interior-point methods for the monotone semidefinite
                  linear complementarity problem in symmetric matrices}
}

@inproceedings{DK97a,
    author = "Daphne Koller and Mehran Sahami",
    title = "Hierarchically classifying documents using very few words",
    booktitle = "Proceedings of {ICML}-97, 14th International Conference on Machine Learning",
    publisher = "Morgan Kaufmann Publishers, San Francisco, US",
    address = "Nashville, US",
    editor = "Douglas H. Fisher",
    pages = "170--178",
    year = "1997",
    url = "citeseer.ist.psu.edu/koller97hierarchically.html" 
}

@inproceedings{DK97a-short,
    author = "Daphne Koller and Mehran Sahami",
    title = "Hierarchically classifying documents using very few words",
    booktitle = "ICML",
    year = "1997"}


@Article{LYK88a,
  author = 	 {L. Yu. Kolotilina},
  title = 	 {Explicit preconditioning of systems of linear algebraic
equations with dense matrices},
  journal = 	 {J. Sov. Math.},
  year = 	 {1988},
  volume =	 {43},
  pages =	 {2566--2573},
  note =	 {English translation
of a paper first published in {\em Zapiski Nauchnykh Seminarov
Leningradskogo Otdeleniya Matematicheskogo Instituta im. V. A. Steklova
AN SSSR}, 154:90--100, 1986}
}

@techreport{PK05a,
  title={Making Logistic Regression A Core Data Mining Tool: A Practical Investigation of Accuracy, Speed, and Simplicity},
  author={Komarek, Paul and Moore, Andrew W.},
  number =	 {TR-05-27},
  year={2005},
  institution={Robotics Institute, Carnegie Mellon University}
}

@techreport{PK05a-short,
  title={Making Logistic Regression A Core Data Mining Tool},
  author={Komarek, Paul and Moore, Andrew W.},
  year={2005},
  institution={Carnegie Mellon University}
}

@inproceedings{XK14a,
  author = {Xiangnan Kong and Zhaoming Wu and Li-Jia Li and Ruofei Zhang
and Philip S. Yu and Hang Wu and Wei Fan},
  title = {Large-Scale Multi-Label Learning with Incomplete Label
Assignments},
  booktitle = {Proceedings of SIAM International Conference on
Data Mining},
  year={2014},
  pages = {920--928}
}

@inproceedings{XK14a-short,
  author = {Xiangnan Kong and Zhaoming Wu and Li-Jia Li and Ruofei Zhang
and Philip S. Yu and Hang Wu and Wei Fan},
  title = {Large-Scale Multi-Label Learning with Incomplete Label
Assignments},
  booktitle = {SDM},
  year={2014}
}

@article{JAK97a,
        author = {Joseph A. Konstan and Bradley N. Miller and David Maltz and Jonathan L. Herlocker and Lee R. Gordon and John Riedl},
        title = {{G}roup{L}ens: applying collaborative filtering to {U}senet news},
        journal = {Communications of the ACM},
        volume = {40},
        number = {3},
        year = {1997},
        issn = {0001-0782},
        pages = {77--87},
        doi = {http://doi.acm.org/10.1145/245108.245126},
        publisher = {ACM},
        address = {New York, NY, USA},
}

@article{HK10a,
 author = {K\"{o}pcke, Hanna and Rahm, Erhard},
 title = {Frameworks for entity matching: a comparison},
 journal = {Data and Knowledge Engineering},
 volume = {69},
 number = {2},
 year = {2010},
 pages = {197--210},
}

@inproceedings{HK10b,
 author = {K\"{o}pcke, Hanna and Thor, Andreas and Rahm, Erhard},
 title = {Evaluation of entity resolution approaches on real-world match problems},
 booktitle = {Proceedings of the VLDB Endowment},
 year = {2010},
 pages = {484--493},
}

@inproceedings{YK08a,
 author = {Koren, Yehuda},
 title = {Factorization meets the neighborhood: a multifaceted collaborative filtering model},
 booktitle = {Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining},
 series = {KDD '08},
 year = {2008},
 isbn = {978-1-60558-193-4},
 location = {Las Vegas, Nevada, USA},
 pages = {426--434},
 numpages = {9},
 url = {http://doi.acm.org/10.1145/1401890.1401944},
 doi = {10.1145/1401890.1401944},
 acmid = {1401944},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {collaborative filtering, recommender systems},
} 

@article{YK09a,
	title={Matrix Factorization Techniques for Recommender Systems},
	volume={42}, 
	journal={Computer}, 
	publisher={IEEE}, 
	author={Koren, Yehuda and Bell, Robert M. and Volinsky, Chris}, 
	year={2009}, 
	pages={30--37}
}

@article{YK09a-short,
	title={Matrix Factorization Techniques for Recommender Systems},
	volume={42}, 
	journal={Computer}, 
	author={Koren, Yehuda and Bell, Robert M. and Volinsky, Chris}, 
	year={2009}, 
}

@techreport{YK09b,
  title =	 {The {BellKor} Solution to the {Netflix} Grand Prize},
  author =	 {Yehuda Koren},
  year =	 {2009}
}

@incollection{YK11a,
year={2011},
booktitle={Recommender Systems Handbook},
editor={Ricci, Francesco and Rokach, Lior and Shapira, Bracha and Kantor, Paul B.},
title={Advances in Collaborative Filtering},
publisher={Springer US},
author={Koren, Yehuda and Bell, Robert},
pages={145--186},
}


@Misc{RK98a,
  author =	 {R. Kouhia},
  note =	 {Private communication}
}


@inproceedings{JK01a,
 author = {James T. Kwok},
 title = {Linear Dependency between epsilon and the Input Noise in epsilon-Support Vector Regression},
 booktitle = {Proceedings of the International Conference on Artificial Neural Networks},
 year = {2001},
 isbn = {3-540-42486-5},
 pages = {405--410},
 publisher = {Springer-Verlag},
 }

@inproceedings{OOK15a,
 author = {Koyejo, Oluwasanmi O. and Natarajan, Nagarajan and Ravikumar, Pradeep K. and Dhillon, Inderjit S.},
 booktitle = {Advances in Neural Information Processing Systems},
 title = {Consistent Multilabel Classification},
 volume = {28},
 year = {2015}
}

@InProceedings{Kreel99,
  author	= {Ulrich H.-G. Kressel},
  title		= {Pairwise Classification and Support Vector Machines},
  publisher	= {{MIT} Press},
  year		= {1998},
  pages		= {255--268},
  booktitle	= {Advances in Kernel Methods -- Support Vector Learning},
  editor	= {B.~Sch{\"o}lkopf and C. J. C.~Burges and A. J.~Smola},
  address	= {Cambridge, MA}
}

@inproceedings{WK19a,
title={Efficient Training on Very Large Corpora via Gramian Estimation},
author={Krichene, Walid and Mayoraz, Nicolas and Rendle, Steffen and Zhang, Li and Yi, Xinyang and Hong, Lichan and Chi, Ed and Anderson, John},
booktitle={International Conference on Learning Representations},
year={2019}
}

@inproceedings{WK19a-short,
title={Efficient Training on Very Large Corpora via Gramian Estimation},
author={Krichene, Walid and Mayoraz, Nicolas and Rendle, Steffen and Zhang, Li and Yi, Xinyang and Hong, Lichan and Chi, Ed and Anderson, John},
booktitle={ICLR},
year={2019}
}

@inproceedings{HPK09a,
  title={{LoOP}: local outlier probabilities},
  author={Hans-Peter Kriegel and Peer Kr{\"o}ger and Erich Schubert and Arthur Zimek},
  booktitle={Proceedings of the 18th ACM Conference on Information and Knowledge Management (CIKM)},
  year={2009}
}

@inproceedings{HPK11a,
  author = {Hans-Peter Kriegel and Peer Kroger and Erich Schubert and Arthur Zimek},
  title = {Interpreting and Unifying Outlier Scores},
  booktitle = {Proceedings of SIAM International Conference on Data Mining (SDM)},
  year = {2011},
  pages = {13--24}
}

@Article{BK04a,
 author =       {Balaji Krishnapuram and Alexander
J. Hartemink and  Lawrence Carin and M\'{a}rio A. T. Figueiredo},
 title =        {A {B}ayesian approach to joint feature selection and
classifier design},
journal =      {IEEE Transactions on Pattern Analysis and Machine Intelligence},
 year =         {2004},
 volume =       {26},
 number =       {6},
 pages =        {1105--1111}
}

@Article{BK05a,
 author =       {Balaji Krishnapuram and Lawrence Carin and M\'{a}rio A.
T. Figueiredo and Alexander J. Hartemink},
 title =        {Sparse multinomial logistic regression: fast
algorithms and generalization bounds},
journal =      {IEEE Transactions on Pattern Analysis and Machine Intelligence},
 year =         {2005},
 volume =       {27},
 number =       {6},
 pages =        {957--968}
}

@techreport{AK09a,
   title={Learning multiple layers of features from tiny images},
   author={Krizhevsky, Alex},
   year={2009},
   institution = {University of Toronto}
}

@incollection{AK12b,
    title = {{I}mage{N}et Classification with Deep Convolutional Neural
Networks},
    author = {Alex Krizhevsky and Sutskever, Ilya and Geoffrey E. Hinton},
    booktitle = {Advances in Neural Information Processing Systems 25},
    editor = {F. Pereira and C. J. C. Burges and L. Bottou and K. Q.
Weinberger},
    pages = {1097--1105},
    year = {2012}
}

@inproceedings{AKG12a,
  title={Multi-relational matrix factorization using bayesian personalized ranking for social network data},
  author={Krohn-Grimberghe, Artus and Drumond, Lucas and Freudenthaler, Christoph and Schmidt-Thieme, Lars},
  booktitle={Proceedings of the fifth ACM International Conference on Web Search and Data Mining (WSDM)},
  pages={173--182},
  year={2012}
}

@InProceedings{TK00a,
author = {Taku Kudo and Yuji Matsumoto},
title = {Japanese Dependency Structure Analysis Based on Support  
Vector Machines},
booktitle = {Proceedings of the 2000 Joint SIGDAT conference on Empirical methods in natural language processing and very large corpora},
year = {2000}
}

@inproceedings{TK03a,
author = {Taku Kudo and Yuji Matsumoto},
title = {Fast Methods for Kernel-based Text Analysis},
booktitle =    {Proceedings of the 41st Annual Meeting of the Association of Computational Linguistics (ACL)},
year={2003}
}

@inproceedings{TK03a-short,
author = {Taku Kudo and Yuji Matsumoto},
title = {Fast Methods for Kernel-based Text Analysis},
booktitle =    {ACL},
year={2003}
}

@inproceedings{TK04a,
 author = {Kudo, Taku and Matsumoto, Yuji},
 title = {A Boosting Algorithm for Classification of Semi-structured Text},
 booktitle = {Proceedings of Empirical Methods in Natural Language Processing},
 year = {2004}
}

@unpublished{JK09a,
   author = "Jussi Kujala and Timo Aho and Tapio Elomaa",
   title = "A walk from 2-Norm {SVM} to 1-Norm {SVM}",
   note = {Preprint available from \url{http://www.cs.tut.fi/~kujala2/papers/1norm2norm.pdf}},
   year = "2009"
}

@article{SK12a,
 author = {Kumar, Sanjiv and Mohri, Mehryar and Talwalkar, Ameet},
 title = {Sampling Methods for the Nystr\"{o}M Method},
 journal = {Journal of Machine Learning Research},
 year = {2012},
 volume={13},
 pages = {981--1006},
}


@InProceedings{TMK14a,
  author = 	 {Tzu-Ming Kuo and Ching-Pei Lee and Chih-Jen Lin},
  title = 	 {Large-scale Kernel Rank{SVM}},
  OPTcrossref =  {},
  OPTkey = 	 {},
  booktitle =	 {Proceedings of SIAM International Conference on Data Mining (SDM)},
  OPTpages = 	 {},
  year =	 {2014},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTaddress = 	 {},
  OPTmonth = 	 {},
  OPTorganization = {},
  OPTpublisher = {},
  OPTnote = 	 {},
  url = {http://www.csie.ntu.edu.tw/~cjlin/papers/ranksvm/kernel.pdf},
  OPTannote = 	 {}
}

@inproceedings{TTK10a,
	title={Designing, Analyzing and Exploiting Stake-Based Social Networks},
	author={Tsung-Ting Kuo and Jung-Jung Yeh and Chia-Jen Lin and Shou-De Lin},
	booktitle={2010 International Conference on Advances in Social Networks Analysis and Mining},
	pages={402--403},
	year={2010},
	organization={IEEE}
}

@inproceedings{TTK10b,
	title={StakeNet: Devise, Study and Utilize Social Networks Using Stakeholder Information},
	author={Tsung-Ting Kuo and Jung-Jung Yeh and Chia-Jen Lin and Shou-De Lin},
	booktitle={2010 International Conference on Technologies and Applications of Artificial Intelligence},
	pages={86--93},
	year={2010},
	organization={IEEE}
}

@article{TTK11a,
  title={Learning-based concept-hierarchy refinement through exploiting topology, content and social information},
  author={Tsung-Ting Kuo and Shou-De Lin},
  journal={Information Sciences},
  volume={181},
  number={12},
  pages={2512--2528},
  year={2011}
}


@article{FRK01a,
  title={Factor graphs and the sum-product algorithm},
  author={Kschischang, Frank R. and Frey, Brendan J. and Loeliger, Hans-Andrea},
  journal={IEEE Transactions on Information Theory},
  volume={47},
  number={2},
  pages={498--519},
  year={2001}
}

@ONLINE{KYOCERA12a,
author = {KYOCERA},
title = {URBANO PROGRESSO},
howpublished = {\url{http://www.kyocera.co.jp/}}
}

@inproceedings{AK12a,
title = {Graph{C}hi: large-scale graph computation on just a {PC}},
author = {Aapo Kyrola and Guy Blelloch and Carlos Guestrin},
booktitle = {Proceedings of the 10th USENIX Symposium on
	Operating Systems Design and Implementation
	(OSDI)},
year = {2012}
}

@Book{la:si,
author =       "P.V. Laarhoven and E. Aarts",
title =        "Simulated annealing: Theory and applications",
publisher =    "Reidel Pub.",
year =         "1987",
address =      "Dordrecht, Holland"
}


@inproceedings{LL11a,
  author    = {Lubor Ladicky and
               Philip H. S. Torr},
  title     = {Locally Linear Support Vector Machines},
  booktitle = {Proceedings of the 28th International Conference on Machine Learning (ICML)},
  pages     = {985--992},
  year      = {2011},
}

@inproceedings{LL11a-short,
  author    = {Lubor Ladicky and
               Philip H. S. Torr},
  title     = {Locally Linear Support Vector Machines},
  booktitle = {ICML},
  year      = {2011},
}

@inproceedings{DL14a,
  title = {Towards better measurement of attention and satisfaction in mobile search},
  author = {Lagun, Dmitry and Hsieh, Chih-Hung and Webster, Dale and Navalpakkam, Vidhya},
  booktitle = {Proceedings of the 37th international ACM SIGIR conference on Research and development in information retrieval},
  pages = {113--122},
  year = {2014}
}

@inproceedings{DL14a-short,
  title = {Towards better measurement of attention and satisfaction in mobile search},
  author = {Lagun, Dmitry and Hsieh, Chih-Hung and Webster, Dale and Navalpakkam, Vidhya},
  booktitle = {SIGIR},
  year = {2014}
}

@Article{DL04a,
  author = 	 {D. Lai and M. Palaniswami and N. Mani},

  title = 	 {A new heuristic-driven decomposition method for training support vector machines},
  journal = 	 {IEEE Transactions on Neural Networks},
  year = 	 {},
  OPTkey = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTpages = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}


@TechReport{DL03a,
  author = 	 {D. Lai and  N. Mani and M. Palaniswami},
  title = 	 {Increasing the step of the {N}ewtonian Decomposition
Method for Support Vector Machines},
  number =       {MECSE-29-2003},
  year = 	 {2003},
  institution =  {Dept. Electrical and Computer Systems Engineering
Monash University, Australia},
  OPTkey = 	 {},
  OPTnumber = 	 {},
  OPTaddress = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

%  title = 	 {A new method to select working sets for faster training for support vector machines},

@TechReport{DL03b,
  author = 	 {D. Lai and N. Mani and  M. Palaniswami},
  title = 	 {A new method to select working sets for faster training for
support vector machines},
  number =       {MESCE-30-2003},
  year = 	 {2003},
  institution =  {Dept. Electrical and Computer Systems Engineering
Monash University, Australia},
  OPTkey = 	 {},
  OPTtype = 	 {},
  OPTnumber = 	 {},
  OPTaddress = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@inproceedings{HL17a,
title={The selective labels problem: Evaluating algorithmic predictions in the presence of unobservables},
author={Lakkaraju, Himabindu and Kleinberg, Jon and Leskovec, Jure and Ludwig, Jens and Mullainathan, Sendhil},
booktitle={Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)},
pages={275--284},
year={2017}
}


@inproceedings{HL17a-short,
title={The selective labels problem: Evaluating algorithmic predictions in the presence of unobservables},
author={Lakkaraju, Himabindu and Kleinberg, Jon and Leskovec, Jure and Ludwig, Jens and Mullainathan, Sendhil},
booktitle={KDD},
year={2017}
}

@article{GRGL04a,
  title={{Learning the Kernel Matrix with Semidefinite Programming}},
  author={Lanckriet, G.R.G. and Cristianini, N. and Bartlett, P. and El Ghaoui, L. and Jordan, M.I.},
  journal={Journal of Machine Learning Research},
  volume={5},
  pages={27--72},
  year={2004},
  publisher={MIT Press Cambridge, MA, USA}
}


@inproceedings{JL01a,
  title={Conditional Random Fields: Probabilistic Models for Segmenting and Labeling 
Sequence Data},
  author={Lafferty, J. and McCallum, A. and Pereira, F.},
  pages={282--289},
  year={2001},
  booktitle = {Proceedings of the 18th International Conference on
               Machine Learning (ICML)}
}


@inproceedings{KL95a,
author = "Ken Lang",
title = "Newsweeder: Learning to filter netnews",
year = 1995,
booktitle = "Proceedings of the Twelfth International Conference on Machine Learning",
pages = "331--339"
}

@inproceedings{KL95a-short,
author = "Ken Lang",
title = "Newsweeder: Learning to filter netnews",
year = 1995,
booktitle = "ICML",
pages = "331--339"
}


@Article{KL00a,
  author = {Kenneth Lange and David R. Hunter and Ilsoon Yang},
  title = {Optimization Transfer Using Surrogate Objective Functions},
  journal = {Journal of Computational and Graphical Statistics},
  year = {2000},
  volume = {9},
  pages = {1--20},
  number = {1},
  month = {March}
}

@Article{KL00a-short,
  author = {Kenneth Lange and David R. Hunter and Ilsoon Yang},
  title = {Optimization Transfer Using Surrogate Objective Functions},
  journal = {J. Comput. Graph. Statist.},
  year = {2000},
  volume = {9},
  pages = {1--20},
  number = {1},
  month = {March}
}

@Misc{JL07a,
  author = {John Langford and Lihong Li and Alex Strehl},
  title = {Vowpal {W}abbit},
  year = {2007},
  note = {\url{https://github.com/JohnLangford/vowpal_wabbit/wiki}}
 }


@ARTICLE{JL09a,
  author = {John Langford and Lihong Li and Tong Zhang},
  title = {Sparse Online Learning via Truncated Gradient},
  journal = {Journal of Machine Learning Research },
  volume = {10},
  year = {2009},
  pages ={771--801}
}

@ARTICLE{JL09a-short,
  author = {John Langford and Lihong Li and Tong Zhang},
  title = {Sparse Online Learning via Truncated Gradient},
  journal = {JMLR},
  volume = {10},
  year = {2009},
  pages ={771--801}
}

@Misc{RML98a,
  title={Lanczos bidiagonalization with partial reorthogonalization},
  author={Larsen, Rasmus Munk},
  year={1998}
}

@inproceedings{CL17a,
title={Counterfactual Learning from Bandit Feedback under Deterministic Logging: A Case Study in Statistical Machine Translation},
author={Lawrence, Carolin and Sokolov, Artem and Riezler, Stefan},
booktitle={Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing},
pages={2566--2576},
year={2017}
}

@inproceedings{CL17a-short,
title={Counterfactual Learning from Bandit Feedback under Deterministic Logging: A Case Study in Statistical Machine Translation},
author={Lawrence, Carolin and Sokolov, Artem and Riezler, Stefan},
booktitle={EMNLP},
year={2017}
}

@incollection{JL09c,
 title = {Slow Learners are Fast},
 author = {John Langford and Alex Smola and Martin Zinkevich},
 booktitle = {Advances in Neural Information Processing Systems 22}, 
 editor = {Y. Bengio and D. Schuurmans and J. Lafferty and C. K. I. Williams and A. Culotta}, 
 pages = {2331--2339}, 
 year = {2009}
}

@incollection{JL09c-short,
 title = {Slow Learners are Fast},
 author = {John Langford and Alex Smola and Martin Zinkevich},
 booktitle = {{NIPS} 22},
 year = {2009}
}


@InProceedings{PL99a,
  author = 	 {P. Laskov},
  title = 	 {An improved decomposition algorithm for regression support vector machines},
  booktitle = 	 {Workshop on {S}upport {V}ector {M}achines, {NIPS}99},
  year =	 {1999}
}


@Article{PL01a,
  author = 	 {P. Laskov},
  title = 	 {An improved decomposition algorithm for regression support vector machines},
  year = 	 {2002},
 volume = {46},
journal={Machine Learning},
pages={315--350}
}

@article{PL06b,
	title={Incremental support vector learning: Analysis, implementation and applications},
	author={Laskov, Pavel and Gehl, Christian and Kr{\"u}ger, Stefan and M{\"u}ller, Klaus-Robert},
	journal={Journal of Machine Learning Research},
	volume={7},
	pages={1909--1936},
	year={2006}
}
@article{PL06b-short,
	title={Incremental support vector learning: Analysis, implementation and applications},
	author={Laskov, Pavel and Gehl, Christian and Kr{\"u}ger, Stefan and M{\"u}ller, Klaus-Robert},
	journal={JMLR},
	volume={7},
	pages={1909--1936},
	year={2006}
}


@InProceedings{MHL01,
  author = 	 {Law, M. H. and J. T. Kwok},
  title = 	 {Bayesian support vector regression},
  booktitle = 	 {Proceedings of the Eighth International Workshop on
  Artificial Intelligence and Statistics (AISTATS)},
  year =	 {2001},
  pages =	 {239--244},
  address =	 {Key West, Florida, USA}
}

@article{ELL63,
	 author = "Lawler, E.L.",
	 title = "The quadratic assignment problem",
	 journal = {Management Sci.},
	 volume = "9",
	 pages = "586--599",
	 year = "1963"
	 }



@Book{CLL74a,
  author =	 {Lawson, C. L. and R. J. Hanson},
  ALTeditor = 	 {},
  title = 	 {Solving Least Squares Problems},
  publisher = 	 {Prentice-Hall},
  year = 	 {1974},
  OPTkey = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTaddress = 	 {},
  OPTedition = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}


@article{CLL79a,
 author = {Lawson, Charles L. and Hanson, Richard J. and Kincaid, David R. and Krogh, Fred T.},
 title = {Basic Linear Algebra Subprograms for {F}ortran Usage},
 journal = {ACM Transactions on Mathematical Software},
 volume = {5},
 number = {3},
 year = {1979},
 pages = {308--323}
}

@article{CLL79a-short,
 author = {Lawson, Charles L. and Hanson, Richard J. and Kincaid, David R. and Krogh, Fred T.},
 title = {Basic Linear Algebra Subprograms for {F}ortran Usage},
 journal = {ACM TOMS},
 volume = {5},
 year = {1979},
 pages = {308--323}
}

@inproceedings{QVL11a,
  title = {On Optimization Methods for Deep Learning},
  author = {Le, Quoc V. and Ngiam, Jiquan and Coates, Adam and Lahiri,  
Abhik and Prochnow, Bobby and Ng, Andrew Y.},
  booktitle = {Proceedings of the 28th International Conference on  
Machine Learning},
  pages = {265--272},
  year = {2011}
}

@inproceedings{QVL13a,
title = {Fastfood - Approximating Kernel Expansions in Loglinear Time},
author  = {Quoc V. Le and Tamas Sarlos and Alex Smola},
year  = {2013},
booktitle = {Proceedings of the 30th International Conference on Machine Learning (ICML)}
}

@inproceedings{QVL13a-short,
title = {Fastfood - Approximating Kernel Expansions in Loglinear Time},
author  = {Quoc V. Le and Tamas Sarlos and Alex Smola},
year  = {2013},
booktitle = {ICML}
}

@INCOLLECTION{GL02a,
  author = {Guy Lebanon and John Lafferty},
  title = {Boosting and Maximum Likelihood for Exponential Models},
  booktitle = {Advances in Neural Information Processing Systems 14},
  publisher = {MIT Press}, 
  year = {2002}
} 

@inproceedings{GL06a,
      title={Speed-Up LOO-CV with SVM Classifier},
        author={Gilles Lebrun and Olivier L{\'e}zoray and Christophe Charrier and Hubert Cardot},
booktitle={Proceedings of International Conference on Intelligent Data Engineering and Automated Learning (IDEAL)},
pages="108--115",
      year={2006}
}

@unpublished{VL16a,
  TITLE = {Probabilistic Approach to One-Class Support Vector Machine},
  AUTHOR = {Lecl{\`e}re, Vincent and Grave, Edouard and El Ghaoui, Laurent},
  YEAR = {2016}
}

@article{YL89a,
  title={Backpropagation applied to handwritten zip code recognition},
  author={{LeCun}, Yann and Boser, Bernhard and Denker, John S. and Henderson, Donnie and Howard, Richard E. and Hubbard, Wayne and Jackel, Lawrence D.},
  journal={Neural Computation},
  volume={1},
  number={4},
  pages={541--551},
  year={1989}
}

@Article{YL98a,
  author = {Yann {LeCun} and Bottou, L{\'e}on and Bengio, Yoshua and  Haffner, Patrick},
  title = {Gradient-based learning applied to document recognition},
  note =  {{MNIST} database available at \url{http://yann.lecun.com/exdb/mnist/}},
  journal = 	 {Proceedings of the IEEE},
  year = 	 {1998},
  OPTkey = 	 {},
  volume =	 {86},
  number =	 {11},
  pages =	 {2278--2324},
  month =	 {November},
  OPTnote = 	 {},
  OPTannote = 	 {}
}


@inproceedings{YL98b,
  author = {{LeCun}, Yann and Bottou, L\'{e}on and Orr, Genevieve B. and M{\"{u}}ller, Klaus-Robert},
  title = {Efficient Backprop},
  bookTitle={Neural Networks: Tricks of the Trade},
  pages = {9--50},  
  year = {1998},
  publisher = {Springer Verlag}  
}

@InProceedings{YL95a,
  author = 	 "Y. {LeCun} and  L.D. Jackel and  L. Bottou and  A. Brunot and  C. Cortes and 
     J.S. Denker and  H. Drucker and  I. Guyon and  U.A. Muller and  E. Sackinger and  P. Simard
     and V. Vapnik",
  title = 	 "Comparison of learning algorithms for handwritten digit
     recognition",
  year =	 "1995",
  booktitle  =   "International Conference on Artificial Neural Networks",
  pages =	 "53--60",
  editor      =  {F.Fogelman and P.Gallinari},
  address =	 "Paris, 1995. EC2 \& Cie."
}

@inproceedings{YL04b,
   title={Learning methods for generic object recognition with  
invariance to pose and lighting},
 author = {{LeCun}, Yann and Huang, Fu Jie and Bottou, L{\'e}on},
 booktitle = {Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition},
 pages = {97--104}, 
   year={2004}
}

@MastersThesis{CYL08a,
  author = {Cheng-Yu Lee},
  title = {A Comparison of Optimization Methods for Large-scale
L1-regularized Logistic Regression},
  school = {Department of Computer Science and Information
Engineering, National Taiwan University},
  year = {2008}
}

@Article{CPL12a,
author = {Ching-Pei Lee and Chih-Jen Lin},
title = {A Study on {L}2-Loss (Squared Hinge-Loss) Multi-Class {SVM}},
year = 	 {2013},
journal = {Neural Computation},
volume={25},
number={5},
pages={1302--1323},
url={http://www.csie.ntu.edu.tw/~cjlin/papers/l2mcsvm/l2mcsvm.pdf}
}

@Article{CPL13a,
author = {Ching-Pei Lee and Chih-Jen Lin},
title = {Large-scale Linear Rank{SVM}},
year = 	 {2014},
journal = {Neural Computation},
url = {http://www.csie.ntu.edu.tw/~cjlin/papers/ranksvm/ranksvml2.pdf},
volume={26},
number={4},
pages={781--817}
}

@article{CPL13a-short,
author = {Ching-Pei Lee and Chih-Jen Lin},
title = {Large-scale Linear Rank{SVM}},
year = {2014},
journal = {Neural Computation},
note = {To appear}
}

@inproceedings{CPL15a,
  author    = {Ching-Pei Lee and Dan Roth},
  title     = {Distributed Box-Constrained Quadratic Optimization for Dual Linear {SVM}},
  booktitle = {Proceedings of the 32nd International Conference on
               Machine Learning (ICML)},
  year      = {2015}
}

@inproceedings{CPL15a-short,
  author    = {Ching-Pei Lee and Dan Roth},
  title     = {Distributed Box-Constrained Quadratic Optimization for Dual Linear {SVM}},
  booktitle = {ICML},
  year      = {2015}
}

@misc{CPL16a,
  title={Random Permutations Fix a Worst Case for Cyclic Coordinate Descent},
  author={Ching-Pei Lee and Stephen J. Wright},
  note={arXiv preprint arXiv:1607.08320},
  year={2016}
}


@InProceedings{CPL17a,
  author = {Ching-Pei Lee and Po-Wei Wang and Weizhu Chen and Chih-Jen Lin},
  title = {Limited-memory Common-directions Method for
Distributed Optimization and its Application on
Empirical Risk Minimization},
  booktitle =	 {Proceedings of SIAM International Conference on Data Mining (SDM)},
  year =	 {2017},
  url={http://www.csie.ntu.edu.tw/~cjlin/papers/l-commdir/l-commdir.pdf}
}

@InProceedings{CPL17a-short,
  author = {Ching-Pei Lee and Po-Wei Wang and Weizhu Chen and Chih-Jen Lin},
  title = {Limited-memory Common-directions Method for
Distributed Optimization and its Application on
Empirical Risk Minimization},
  booktitle =	 {SDM},
  year =	 {2017}
}

@article{CPL20a,
  author = {Ching-Pei Lee and Po-Wei Wang and Chih-Jen Lin},
  title = {Limited-memory common-directions method for large-scale optimization: convergence, parallelization, and distributed optimization},
  journal = 	 {Mathematical Programming Computation},
  year =	 {2022},
  url = {https://www.csie.ntu.edu.tw/~cjlin/papers/l-commdir-journal/l-commdir.pdf},
  volume =	 {14},
  OPTnumber = 	 {},
  pages =	 {543--591}
}

@Article{DDL99a,
  author = 	 {Daniel D. Lee and H. Sebastian Seung},
  title = 	 {Learning the parts of objects by non-negative matrix factorization},
  journal = 	 {Nature},
  year = 	 {1999},
  OPTkey = 	 {},
  volume =	 {401},
  OPTnumber = 	 {},
  pages =	 {788--791},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@InProceedings{DDL01a,
  author    = {Daniel D. Lee and H. Sebastian Seung},
  title     = {Algorithms for Non-negative Matrix Factorization},
  booktitle = {Advances in Neural Information Processing Systems 13},
  pages     = {556--562},
  year      = {2001},
  editor    = {Leen, Todd K. and Dietterich, Thomas G. and Tresp, Volker},
  publisher = {MIT Press}
}

@InProceedings{DDL01a-short,
  author    = {Daniel D. Lee and H. Sebastian Seung},
  title     = {Algorithms for Non-negative Matrix Factorization},
  booktitle = {{NIPS} 13},
  year      = {2001},
}

@article{GL10a,
  author = {Lee, Gyemin and Scott, Clayton},
  title = {Nested Support Vector Machines},
  year = {2010},
  volume = {58},
  number = {3},
  doi = {10.1109/TSP.2009.2036071},
  journal = {IEEE Transactions on Signal Processing},
  pages = {1648--1660}
}

@InCollection{HL07a,
	author = {Honglak Lee and Alexis Battle and Rajat Raina and Andrew Y. Ng},
	title = {Efficient Sparse Coding Algorithms},
	booktitle = {Advances in Neural Information Processing Systems},
	pages = {801--808},
	year = {2007}
}

@TechReport{JHLee00a,
  author = 	 {Jen-Hao Lee and Chih-Jen Lin},
  title = 	 {Automatic model selection for support vector machines},
  institution =  {Department of Computer Science and
Information Engineering, 
National Taiwan University},
  year = 	 {2000}
}

@TechReport{JHLee00a-short,
  author = 	 {J.-H. Lee and C.-J. Lin},
  title = 	 {Automatic model selection for support vector machines},
  year = 	 {2000}
}



@MastersThesis{JHL01a,
  author = 	 {Jen-Hao Lee},
  title = 	 {Model Selection of the Bounded {SVM} Formulation Using the {RBF} Kernel},
  school = 	 {Department of Computer Science and Information Engineering, National Taiwan University},
  year = 	 {2001}
}

@TechReport{ML01a,
  author = 	 {Martin M.S. Lee and  S. Sathiya  Keerthi and Chong Jin Ong
and Dennis DeCoste},
  title = 	 {An Efficient Method for Computing Leave-One-Out
Error in Support Vector Machines
},
  institution =  {Department of Mechanical and Production Engineering, National University of Singapore
},
  year = 	 {2001},
  address =	 {Singapore}
}



@inproceedings{MCL15a,
  author = 	 {Mu-Chu Lee and Wei-Lin Chiang and Chih-Jen Lin},
  title = 	 {Fast Matrix-vector Multiplications for Large-scale Logistic Regression on Shared-memory Systems},
  year = 	 {2015},
 booktitle = {Proceedings of the IEEE International Conference on Data Mining (ICDM)},
  url={http://www.csie.ntu.edu.tw/~cjlin/papers/multicore_liblinear_icdm.pdf}, 
  OPTkey = 	 {},
  OPTtype = 	 {},
  OPTnumber = 	 {},
  OPTaddress = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@inproceedings{MCL15a-short,
  author = 	 {Mu-Chu Lee and Wei-Lin Chiang and Chih-Jen Lin},
  title = 	 {Fast Matrix-vector Multiplications for Large-scale Logistic Regression on Shared-memory Systems},
  year = 	 {2015},
 booktitle = {ICDM},
  OPTkey = 	 {},
  OPTtype = 	 {},
  OPTnumber = 	 {},
  OPTaddress = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}


@article{SL10a,
 author = {Lee, Sangkyun and Wright, Stephen J.},
 title = {{ASSET}: Approximate Stochastic Subgradient Estimation Training for Support Vector Machines},
 journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
 note = {Submitted},
 year = {2010}
}


@inproceedings{SIL06a,
title = {Efficient L1 Regularized Logistic Regression},
author = {Su-In Lee and Honglak Lee and Pieter Abbeel and Andrew Y. Ng},
booktitle = {Proceedings of the Twenty-first National Conference on
Artificial Intelligence (AAAI-06)},
address = {Boston, MA, USA},
month = {July},
year = 2006,
pages = {1--9},
}

@inproceedings{SIL06a-short,
title = {Efficient {L}1 Regularized Logistic Regression},
author = {S.-I. Lee and H. Lee and P. Abbeel and A. Y. Ng},
booktitle = {AAAI-06},
year = {2006}
}

@article{SWL06a,
  title={Low Resolution Face Recognition Based on Support Vector Data Description},
  author={Lee, Sang-Woong and Park, Jooyoung and Lee, Seong-Whan},
  journal={Pattern Recognition},
  volume={39},
  number={9},
  pages={1809--1812},
  year={2006},
}

@inproceedings{WL03a,
  author={Lee, Wee Sun and Liu, Bing},
  title={Learning with Positive and Unlabeled Examples Using Weighted Logistic Regression},
  booktitle={Proceedings of the Twentieth International Conference on Machine Learning (ICML)},
  year={2003}
}

@inproceedings{WL03a-short,
  author={Lee, Wee Sun and Liu, Bing},
  title={Learning with Positive and Unlabeled Examples Using Weighted Logistic Regression},
  booktitle={ICML},
  year={2003}
}

@article{YL04a,
  title={Multicategory support vector machines},
  author={Lee, Yoonkyung and Lin, Yi and Wahba, Grace},
  journal={Journal of the American Statistical Association},
  volume={99},
  number={465},
  pages={67--81},
  year={2004}
}

@article{YL04a-short,
  title={Multicategory support vector machines},
  author={Lee, Yoonkyung and Lin, Yi and Wahba, Grace},
  journal={JASA},
  volume={99},
  pages={67--81},
  year={2004}
}

@inproceedings{YL18a,
title={How to Impute Missing Ratings?: Claims, Solution, and Its Application to Collaborative Filtering},
author={Lee, Youngnam and Kim, Sang-Wook and Park, Sunju and Xie, Xing},
booktitle={Proceedings of the 2018 International Conference on World Wide Web (WWW)},
pages={783--792},
year={2018}
}

@inproceedings{YL18a-short,
title={How to Impute Missing Ratings?: Claims, Solution, and Its Application to Collaborative Filtering},
author={Lee, Youngnam and Kim, Sang-Wook and Park, Sunju and Xie, Xing},
booktitle={WWW},
year={2018}
}

@InProceedings{YJL01a,
  author = 	 {Yuh-Jye Lee and Olvi L. Mangasarian},
  title = 	 {{RSVM}: Reduced Support Vector Machines},
  booktitle = 	 {Proceedings of the First SIAM International Conference on
          Data Mining},
  year =	 {2001}
}

@InProceedings{YJL01a-short,
  author = 	 {Yuh-Jye Lee and Olvi L. Mangasarian},
  title = 	 {{RSVM}: Reduced Support Vector Machines},
  booktitle = 	 {SDM},
  year =	 {2001}
}

@Article{YJL01b,
  author = 	 {Y.-J. Lee and O. L. Mangasarian},
  title = 	 {{SSVM}: A Smooth Support Vector Machine for Classification},
  journal = 	 {Computational Optimization and Applications},
  year = 	 {2001},
  volume =	 {20},
  number =	 {1},
  pages =	 {5--22}
}

@InProceedings{YJL03a,
  author = 	 {Y.-J. Lee and H.-Y. Lo and S.-Y. Huang},
  title = 	 {Incrementa reduced support vector machine},
  booktitle = 	 {Proceedings of the Interntaional Conference on Informatics Cybernetics and System (ICICS 2003)},
  year =	 {2003}
}

@inproceedings{DL16a,
  title={Large-scale validation of counterfactual learning methods: A test-bed},
  author={Lefortier, Damien and Swaminathan, Adith and Gu, Xiaotao and Joachims, Thorsten and de Rijke, Maarten},
booktitle={NIPS Workshop on Inference and Learning of Hypothetical
and Counterfactual Interventions in Complex Systems},
  year={2016}
}

@Book{ELL83a,
  author =	 {E. L. Lehmann},
  ALTeditor = 	 {},
  title = 	 {Theory of point estimation},
  publisher = 	 {John Wiley \& Sons},
  year = 	 {1983},
  OPTkey = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTaddress = 	 {},
  OPTedition = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@Book{ELL,
author =       "E. L. Lehmann",
title =        "Testing statistical hypotheses",
publisher =    "Wiley",
year =         "1986",
edition =      "2nd",
address =      "New York"
}

@article{EL02a,
  author = {Edda Leopold and J{\"o}rg Kindermann},
  title = {Text Categorization with Support Vector Machines. {H}ow to
Represent Text in Input Space?},
  journal = {Machine Learning},
  year = {2002},
  volume = {46},
  pages = {423--444}
}

@article{ML91,
author      = {M. Lescrenier},
journal     = {SIAM J. Numer. Anal.},
pages       = {476--495},
title       = {Convergence of trust region algorithms for optimization
with bounds when strict complementarity does not hold},
volume      = {28},
year        = {1991}
}

@InProceedings{CL02a,
  author = 	 {Christina Leslie and Eleazar Eskin and William Stafford Noble},
  title = 	 {The spectrum kernel: A string kernel for SVM protein classification},
  booktitle = 	 {Proceedings of the Pacific Symposium on Biocomputing},
  OPTcrossref =  {},
  OPTkey = 	 {},
  pages =	 {564--575},
  year =	 {2002},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTaddress = 	 {},
  OPTmonth = 	 {},
  OPTorganization = {},
  OPTpublisher = {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@article{LL14a,
	title={Analysis and design of optimization algorithms via integral quadratic constraints},
	author={Lessard, Laurent and Recht, Benjamin and Packard, Andrew},
	journal={{SIAM} Journal on Optimization},
	volume={26},
	number={1},
	pages={57--95},
	year={2016}
}

@incollection{JL06a,
  title={A practical approach to recognizing physical activities},
  author={Lester, Jonathan and Choudhury, Tanzeem and Borriello, Gaetano},
  booktitle={Lecture Notes in Computer Science},
  volume={3096},
  year={2006},
  publisher={Springer}
}

@article{KL44a,
   title={A method for the solution of certain non-linear problems in  
least squares},
   author={Levenberg, Kenneth},
   journal={Quarterly of Applied Mathematics},
   volume={2},
   number={2},
   pages={164--168},
   year={1944}
}

@inproceedings{OL14a,
  title={Neural word embedding as implicit matrix factorization},
  author={Levy, Omer and Goldberg, Yoav},
  booktitle={Advances in Neural Information Processing Systems},
  pages={2177--2185},
  year={2014}
}

@inproceedings{OL14a-short,
  title={Neural word embedding as implicit matrix factorization},
  author={Levy, Omer and Goldberg, Yoav},
  booktitle={NIPS},
  pages={2177--2185},
  year={2014}
}

@inproceedings{DL91a,
    author = "D. D. Lewis",
    title = "{Evaluating Text Categorization}",
    booktitle = "Proceedings of Speech and Natural Language Workshop",
    publisher = "Morgan Kaufmann",
    pages = "312--318",
    year = "1991",
    url = "citeseer.ist.psu.edu/lewis91evaluating.html" 
}

@inproceedings{DL92a,
 author = {David D. Lewis},
 title = {An evaluation of phrasal and clustered representations on a text categorization task},
 booktitle = {Proceedings of the 15th annual international ACM SIGIR conference on Research and development in information retrieval},
 year = {1992},
 pages = {37--50},
 numpages = {14},
 publisher = {ACM},
 address = {New York, NY, USA},
} 

@inproceedings{DL92a-short,
 author = {David D. Lewis},
 title = {An evaluation of phrasal and clustered representations on a text categorization task},
 booktitle = {SIGIR}, 
 year = {1992},
}

@article{DL94a,
  title={{A comparison of two learning algorithms for text categorization}},
  author={Lewis, D.D. and Ringuette, M.},
  journal={Third Annual Symposium on Document Analysis and Information Retrieval},
  pages={81--93},
  year={1994}
}


@article{DL96a,
  title={Training algorithms for linear text classifiers},
  author={Lewis, D. D. and Schapire, R. E. and Callan, J. P. and Papka, R.},
  journal={Proceedings of the 19th annual international ACM SIGIR conference on Research and development in information retrieval},
  pages={298--306},
  year={1996},
  publisher={ACM Press New York, NY, USA}
}


@article{DL04b,
  author = {David D. Lewis and Yiming Yang and Tony G. Rose and Fan Li},
  title = {{RCV}1: A new benchmark collection for text categorization
research},
  journal = {Journal of Machine Learning Research},
  year = {2004},
  volume = {5},
  pages = {361--397}
}

@article{DL04b-short,
  author = {David D. Lewis and Yiming Yang and Tony G. Rose and Fan Li},
  title = {{RCV}1: A new benchmark collection for text categorization
research},
  journal = {JMLR},
  year = {2004},
  volume = {5},
  pages = {361--397}
}

@article{CTL09a,
	title={Egocentric Information Abstraction for Heterogeneous Social Networks},
	author={Cheng-Te Li and Shou-De Lin},
	journal={2009 Advances in Social Network Analysis and Mining},
	pages={255--260},
	year={2009},
	publisher={IEEE}
}

@incollection{CTL09b,
	title={Mining Heterogeneous Social Networks for Egocentric Information Abstraction},
	author={Cheng-Te Li and Shou-De Lin},
	booktitle={From Sociology to Computing in Social Networks},
        editor={N. Memon and R. Alhajj},
	pages={35--58},
	year={2010},
	publisher={Springer}
}

@inproceedings{CTL10a,
	title={Communication Structure Discovery via Information Asymmetry in an Organizational Social Network},
	author={Cheng-Te Li and Shou-De Lin},
	booktitle={2010 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology},
	pages={524--527},
	year={2010},
	organization={IEEE}
}

@inproceedings{CTL10b,
	title={Pusic: musicalize microblog messages for summarization and exploration},
	author={Cheng-Te Li and Hung-Che Lai and Chien-Tung Ho and Chien-Lin Tseng and Shou-De Lin},
	booktitle={Proceedings of the 19th International Conference on World Wide Web},
	pages={1141--1142},
	year={2010},
	organization={ACM}
}

@inproceedings{CTL10c,
	title={SocioCrowd: a Social-network-based framework for Crowd simulation},
	author={Cheng-Te Li and Hsun-Ping Hsieh and Tsung-Ting Kuo and Shou-De Lin},
	booktitle={ACM SIGGRAPH 2010 Posters},
	pages={17},
	year={2010},
	organization={ACM}
}

@InProceedings{CTL11a,
  author    = {Cheng-Te Li and Chien-Yuan Wang and Chien-Lin Tseng and Shou-De Lin},
  title     = {Meme{T}ube: A Sentiment-based Audiovisual System for Analyzing and Displaying Microblog Messages},
  booktitle = {Proceedings of the ACL-HLT 2011 System Demonstrations},
  year      = {2011},
  pages     = {32--37}
}

@InProceedings{CTL11b,
  author    = {Cheng-Te Li and Shou-De Lin},
  title     = {Social Flocks: A Crowd Simulation Framework for Social Network Generation, Community Detection, and Collective Behavior Modeling},
  booktitle = {ACM KDD Demonstration},
  year      = {2011}
}

@inproceedings{CTL11c,
	title={Finding influential mediators in social networks},
	author={Cheng-Te Li and Shou-De Lin and Man-Kwan Shan},
	booktitle={Proceedings of the 20th International Conference on World Wide Web},
	pages={75--76},
	year={2011},
	organization={ACM}
}

@inproceedings{CLL14a,
  title={Condensed filter tree for cost-sensitive multi-label classification},
  author={Li, Chun-Liang and Lin, Hsuan-Tien},
  booktitle={Proceedings of the 31th International Conference on Machine Learning (ICML)},
  pages={423--431},
  year={2014}
}

@Article{DL01a,
  author = 	 {Dong-Hui Li and Masao Fukushima},
  title = 	 {On the global convergence of the {BFGS} method for nonconvex unconstrained optimization problems},
  journal = 	 {SIAM Journal on Optimization},
  year = 	 {2001},
  volume={11},
  number={4},
  pages =	 {1054--1064}
}

@inproceedings{FL20a,
  title={{ICD} Coding from Clinical Text Using Multi-Filter Residual Convolutional Neural Network},
  author={Li, Fei and Yu, Hong},
  booktitle={Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI)},  
  pages={8180--8187},
  year={2020},
  doi={10.1609/aaai.v34i05.6331}, 
}

@article{JL21b,
  title={RWNE: A Scalable Random-Walk based Network Embedding Framework with Personalized Higher-order Proximity Preserved},
  author={Li, Jianxin and Ji, Cheng and Peng, Hao and He, Yu and Song, Yangqiu and Zhang, Xinmiao and Peng, Fanzhang},
  journal={Journal of Artificial Intelligence Research},
  volume={71},
  pages={237--263},
  year={2021}
}

@inproceedings{JL19a,
  title={Multi-level network embedding with boosted low-rank matrix approximation},
  author={Li, Jundong and Wu, Liang and Guo, Ruocheng and Liu, Chenghao and Liu, Huan},
  booktitle={Proceedings of the IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining},
  pages={49--56},
  year={2019}
}

@inproceedings{JL16a,
    title = "Discriminative Deep Random Walk for Network Classification",
    author = "Li, Juzheng  and
      Zhu, Jun  and
      Zhang, Bo",
    booktitle = "Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL)",
    year = "2016",
    doi = "10.18653/v1/P16-1095",
    pages = "1004--1013"
}

@article{LL16a,
    author = {Li, Le AND Xu, Junyi AND Xiao, Weidong AND Ge, Bin},
    journal = {PLOS ONE},
    title = {Behavior Based Social Dimensions Extraction for Multi-Label Classification},
    year = {2016},
    volume = {11},
    pages = {1--16},
}

@inproceedings{LL20a,
 author = {Li, Liam and Jamieson, Kevin and Rostamizadeh, Afshin and Gonina, Ekaterina and Ben-tzur, Jonathan and Hardt, Moritz and Recht, Benjamin and Talwalkar, Ameet},
 booktitle = {Proceedings of Machine Learning and Systems},
 pages = {230--246},
 title = {A System for Massively Parallel Hyperparameter Tuning},
 volume = {2},
 year = {2020}
}

@inproceedings{LL11b,
title={Unbiased offline evaluation of contextual-bandit-based news article recommendation algorithms},
author={Li, Lihong and Chu, Wei and Langford, John and Wang, Xuanhui},
booktitle={Proceedings of the fourth ACM international conference on Web search and data mining},
pages={297--306},
year={2011}
}

@inproceedings{LL11b-short,
title={Unbiased offline evaluation of contextual-bandit-based news article recommendation algorithms},
author={Li, Lihong and Chu, Wei and Langford, John and Wang, Xuanhui},
booktitle={WSDM},
year={2011}
}

@InProceedings{ML14b,
  author = 	 {Mu Li and Dave Andersen and Alex Smola and Junwoo Park and Amr Ahmed and Vanja Josifovski and James Long and Eugene Shekita and Bor-Yiing Su},
  title = 	 {Scaling distributed machine learning with the parameter server},
  OPTcrossref =  {},
  OPTkey = 	 {},
  booktitle =	 {Proceedings of the 11th USENIX Symposium on Operating Systems Design and Implementation (OSDI)},
  year =	 {2014},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTpages = 	 {},
  OPTmonth = 	 {},
  OPTaddress = 	 {},
  OPTorganization = {},
  OPTpublisher = {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@inproceedings{PL06a,
 author = {Li, Ping and Hastie, Trevor J. and Church, Kenneth W.},
 title = {Very Sparse Random Projections},
 booktitle = {Proceedings of the 12th ACM SIGKDD International
Conference on Knowledge Discovery and Data Mining},
 pages = {287--296},
 year = {2006}
}


@article{PL07a,
	title = {Nonlinear Estimators and Tail Bounds for Dimension Reduction
in {L}1 Using Cauchy Random Projections},
	author={Ping Li and Trevor J. Hastie and Kenneth W. Church},
	journal = {Journal of Machine Learning Research},
	pages={2497--2532},
	year = {2007}
}

@inproceedings{PL10a,
 author = {Ping Li and Arnd Christian K\"{o}nig},
 title = {b-{B}it Minwise Hashing},
 booktitle = {Proceedings of the Nineteenth International Conference on
World Wide Web},
 pages = {671--680},
 year = {2010}
}

@inproceedings{PL10b,
 author = {Ping Li and Arnd Christian K\"{o}nig and Wenhao Gui},
 title = {b-{B}it Minwise Hashing for Estimating Three-way Similarities},
 booktitle = {Advances in Neural Information Processing Systems},
 year = {2010}
}

@misc{PL10c,
  title={An empirical evaluation of four algorithms for multi-class classification: Mart, abc-mart, robust logitboost, and abc-logitboost},
  author={Li, Ping},
  note={arXiv preprint arXiv:1001.1020},
  year={2010}
}

@techReport{PL11a,
 author = {Ping Li and Anshumali Shrivastava and Joshua Moore and Arnd Christian K\"{o}nig},
 title = {Hashing Algorithms for Large-scale Learning},
 year = {2011},
 institution = {Cornell University},
 url = {http://www.stat.cornell.edu/~li/reports/HashLearning.pdf}
}

@article{PL11b,
 author = {Ping Li and Arnd Christian K\"{o}nig},
 title = {Theory and Applications of b-{B}it Minwise Hashing},
 journal = {Communications of the ACM},
 volume = {54},
 number = {8},
 year = {2011},
 issn = {0001-0782},
 pages = {101--109}
}

@techReport{PL11c,
 author = {Ping Li and Arnd Christian K\"{o}nig},
 title = {Comparing b-{B}it Minwise Hashing with Random Projections},
 year = {2011},
 institution = {Cornell University}
}

@article{QL19a,
title = {Graph representation learning with encoding edges},
author = {Qi Li and Zehong Cao and Jiang Zhong and Qing Li},
journal = {Neurocomputing},
volume = {361},
pages = {29--39},
year = {2019}
}


@inproceedings{SL18a,
  title={Offline evaluation of ranking policies with click models},
  author={Li, Shuai and Abbasi-Yadkori, Yasin and Kveton, Branislav and Muthukrishnan, Shan and Vinay, Vishwa and Wen, Zheng},
  booktitle={Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)},
  pages={1685--1694},
  year={2018}
}

@inproceedings{WJL09a,
  title={Relation regularized matrix factorization},
  author={Li, Wu-Jun and Yeung, Dit-Yan},
  booktitle={Proceedings of the 21st International Joint Conference on Artificial
Intelligence (IJCAI)},
  year={2009}
}

@inproceedings{WJL09a-short,
  title={Relation regularized matrix factorization},
  author={Li, Wu-Jun and Yeung, Dit-Yan},
  booktitle={IJCAI},
  year={2009}
}

@misc{XL19a,
       author = {Li, Xiang and Wang, Shusen and Zhang, Zhihua},
        title = {Do Subsampled {N}ewton Methods Work for High-Dimensional Data?},
         year = "2019",
	  note={arXiv preprint arXiv:1902.04952}
}

@misc{XL19a-short,
       author = {Li, Xiang and Wang, Shusen and Zhang, Zhihua},
        title = {Do Subsampled {N}ewton Methods Work for High-Dimensional Data?},
         year = "2019",
	  note={arXiv}
}

@inproceedings{YL10a,
 author = {Li, Yanen and Hu, Jia and Zhai, Chengxiang and Chen, Ye},
 title = {Improving one-class collaborative filtering by incorporating rich user information},
 booktitle = {Proceedings of the 19th ACM International Conference on Information and Knowledge Management (CIKM)},
 year = {2010},
 pages = {959--968}
} 

@inproceedings{YL10a-short,
 author = {Li, Yanen and Hu, Jia and Zhai, Chengxiang and Chen, Ye},
 title = {Improving One-class Collaborative Filtering by Incorporating Rich User Information},
 booktitle = {CIKM},
 year = {2010}
} 

@inproceedings{DL20a,
title={Personalized Ranking with Importance Sampling},
author={Lian, Defu and Liu, Qi and Chen, Enhong},
booktitle={Proceedings of The Web Conference},
pages={1093--1103},
year={2020}
}

@inproceedings{JL18a,
 author = {Lian, Jianxun and Zhou, Xiaohuan and Zhang, Fuzheng and Chen, Zhongxia and Xie, Xing and Sun, Guangzhong},
 title = {x{DeepFM}: Combining Explicit and Implicit Feature Interactions for Recommender Systems},
 booktitle = {Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)},
 year = {2018},
 pages = {1754--1763}
}

@inproceedings{JL18a-short,
 author = {Lian, Jianxun and Zhou, Xiaohuan and Zhang, Fuzheng and Chen, Zhongxia and Xie, Xing and Sun, Guangzhong},
 title = {x{DeepFM}: Combining Explicit and Implicit Feature Interactions for Recommender Systems},
 booktitle = {KDD},
 year = {2018}
}

@Article{LL03a,
  author = 	 {Li Liao and William Stafford Noble},
  title = 	 {Combining Pairwise Sequence Similiarity and Support Vector Machines for Detecting Remote Protein Evolutionary and Structural Relationships},
  journal = 	 {Journal of Computational Biology},
  year = 	 {2003},
  OPTkey = 	 {},
  volume =	 {10},
  OPTnumber = 	 {},
  pages =	 {857--868},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}


@inproceedings{ML14a,
 author = {Li, Mu and Zhang, Tong and Chen, Yuqiang and Smola, Alexander J.},
 title = {Efficient mini-batch training for stochastic optimization},
 booktitle = {Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining},
 year = {2014},
 pages = {661--670}
} 

@article{WL94a,
title={Sharp {L}ipschitz constants for basic optimal solutions and
basic feasible solutions of linear programs},
author={Li, Wu},
journal={SIAM Journal on Control and Optimization},
volume={32},
number={1},
pages={140--153},
year={1994}
}

@inproceedings{DL15b,
  title={Content-aware collaborative filtering for location recommendation based on human mobility data},
  author={Lian, Defu and Ge, Yong and Zhang, Fuzheng and Yuan, Nicholas Jing and Xie, Xing and Zhou, Tao and Rui, Yong},
  booktitle={Proceedings of IEEE International Conference on Data Mining (ICDM)},
  pages={261--270},
  year={2015}
}

@article{JL21a,
title={MILE: A Multi-Level Framework for Scalable Graph Embedding},
journal={Proceedings of the International AAAI Conference on Web and Social Media (ICWSM)},
author={Liang, Jiongqian and Gurukar, Saket and Parthasarathy, Srinivasan},
year={2021},
pages={361-372}
}


@Article{SPL00a,
  author = 	 {Shuo-Peng Liao and Hsuan-Tien Lin and
 Chih-Jen Lin},
  title = 	 {A note on
the decomposition methods 
for support vector regression},
  year = 	 {2002},
   journal = {Neural Computation},
volume={14},
pages={1267--1281}
}


@InProceedings{Liao01a,
  author = 	 {Shuo-Peng Liao and Hsuan-Tien Lin and
 Chih-Jen Lin},
  title = 	 {A note on
the decomposition methods 
for support vector regression},
  booktitle = 	 {Proceedings of IJCNN},
  year =	 {2001}
}

@MISC{LDS,
  author={{\relax {LIBSVM} Data Sets}},
  year={2007},
  note={\url{https://www.csie.ntu.edu.tw/~cjlin/libsvmtools/datasets}}
}


@article{ZL09a,
	title={Incremental support vector machine learning in the primal and applications},
	author={Liang, Zhizheng and Li, YouFu},
	journal={Neurocomputing},
	volume={72},
	number={10},
	pages={2249--2258},
	year={2009}
}



@Article{AL02a,
  author = 	 {Andy Liaw and Matthew Wiener},
  title = 	 {Classification and regression by random{F}orest},
  journal = 	 {R News},
  year = 	 {2002},
  volume =	 {2/3},
  pages =	 {18--22},
  month =	 {December},
  url = {http://cran.r-project.org/doc/Rnews/Rnews_2002-3.pdf}
}

@article{RL18a,
    title={Tune: A Research Platform for Distributed Model Selection and Training},
    author={Liaw, Richard and Liang, Eric and Nishihara, Robert
            and Moritz, Philipp and Gonzalez, Joseph E and Stoica, Ion},
    journal={arXiv preprint arXiv:1807.05118},
    year={2018}
}

@misc{ML13a,
author = "Moshe Lichman",
year = "2013",
title = "{UCI} Machine Learning Repository",
url = "http://archive.ics.uci.edu/ml",
institution = "University of California, Irvine, School of Information and Computer Sciences" } 

@article{EDL02a,
  title={{Automatic metadata generation \& evaluation}},
  author={Liddy, E.D. and Sutton, S. and Allen, E. and Harwell, S. and Corieri, S. and Yilmazel, O. and Ozgencil, N.E. and Diekema, A. and McCracken, N. and Silverstein, J.},
  journal={Proceedings of the 25th annual international ACM SIGIR conference on Research and development in information retrieval},
  pages={401--402},
  year={2002},
  publisher={ACM Press New York, NY, USA}
}


@article{WL91a,
author = {W. Liebert and K. Pawelzik and H. G. Schuster},
title = {Optimal embeddings of chaotic attractors from
topological considerations},
journal= {Europhys. Lett.},
 volume={14},
 pages ={521},
  year={1991}  
}

@inproceedings{DJL12a,
 author = {Liebling, Daniel J. and Bennett, Paul N. and White, Ryen W.},
 title = {Anticipatory Search: Using Context to Initiate Search},
 booktitle = {Proceedings of the 35th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)},
 year = {2012},
 pages = {1035--1036}
}

@inproceedings{DJL12a-short,
 author = {Liebling, Daniel J. and Bennett, Paul N. and White, Ryen W.},
 title = {Anticipatory Search: Using Context to Initiate Search},
 booktitle = {SIGIR},
 year = {2012}
}

@article{SL99a,
    author = "S. Liehr and K. Pawelzik and J. Kohlmorgen and K. R. M{\"u}ller",
    title = "Hidden {M}arkov mixtures of experts with an application to {EEG} recordings from sleep",
    journal = "Theory in Biosci.",
    volume = "118",
    number = "3--4",
    pages = "246--260",
    year = "1999",
    url = "http://citeseer.nj.nec.com/article/liehr99hidden.html" 
}

@article{DL19a,
  title={Discrete matrix factorization and extension for fast item recommendation},
  author={Lian, Defu and Xie, Xing and Chen, Enhong},
  journal={IEEE Transactions on Knowledge and Data Engineering},
  volume={33},
  number={5},
  pages={1919--1933},
  year={2019}
}

@inproceedings{DL15a,
author = {Darryl Lim and Julian McAuley and Gert Lanckriet},
title = {Top-{N} Recoomendation with Missing Implicit Feedback},
year = {2015},
booktitle = {Proceedings of the Sixth ACM Conference on
Recommender Systems},
pages = {309--312}
}

@inproceedings{DL15a-short,
author = {Darryl Lim and Julian McAuley and Gert Lanckriet},
title = {Top-{N} Recoomendation with Missing Implicit Feedback},
year = {2015},
booktitle = {RecSys},
pages = {309--312}
}

@inproceedings{CYL14a,
  author = 	 {Chieh-Yen Lin and Cheng-Hao Tsai and Ching-Pei Lee and Chih-Jen Lin},
  title = 	 {Large-scale logistic regression and linear support vector machines using {S}park},
 booktitle = {Proceedings of the IEEE International Conference on Big Data},
  year = 	 {2014},
  pages =	 {519--528},
  url={http://www.csie.ntu.edu.tw/~cjlin/papers/spark-liblinear/spark-liblinear.pdf}
}

@inproceedings{CYL14a-short,
  author = 	 {Chieh-Yen Lin and Cheng-Hao Tsai and Ching-Pei Lee and Chih-Jen Lin},
  title = 	 {Large-scale Logistic Regression and Linear Support Vector Machines Using {S}park},
 booktitle = {IEEE BigData},
  year = 	 {2014}
}

@InProceedings{CJL94,
  author = 	 {Chih-Jen Lin and Shu-Cherng Fang and Soon-Yi Wu},
  title = 	 {A dual affine scaling based algorithm for solving
                  linear semi-infinite programming problems},
  booktitle =    {{Advances in Optimization and Application}},
  publisher = 	 {Kluwer Academic Publishers},
  year = 	 {1994},
  editor = 	 {D. Z. Du and J. Sun},
  pages =	 {217--234}
}

@Article{CJL94b,
  author = 	 {Shu-Cherng Fang and Chih-Jen Lin and Soon-Yi Wu},
  title = 	 {On solving convex quadratic semi-infinite programming 
problems},
  journal = 	 {Optimization},
  year = 	 {1994},
  volume =	 {37},
  pages =	 {107-125}
}


@TechReport{CJL95a,
author      = {Chih-Jen Lin and Romesh Saigal},
address     = {Ann Arbor, MI 48109-2117},
institution = {Department of Industrial and Operations Engineering, 
	       University of Michigan},
title       = {A predictor corrector method for semi-definite linear
programming}, 
year        = {1995}
}

@TechReport{CJL95b,
author      = {Chih-Jen Lin and Romesh Saigal},
address     = {Ann Arbor, MI 48109-2117},
institution = {Department of Industrial and Operations Engineering, 
	       University of Michigan},
title       = {An infeasible start predictor corrector method for 
	       semi--definite linear programming}, 
year        = {1995}
}

@Article{CJL95c,
  author = 	 {Chih-Jen Lin and E. K. Yang and Shu-Cherng Fang and Soon-Yi Wu},
  title = 	 {Implementation of an inexact approach to 
solving linear  semi-infinite programming problems},
  journal = 	 {Journal of Computational and Applied Mathematics},
  year = 	 {1995},
  volume =	 {61},
  pages =	 {87--103},
}


@TechReport{CJL96,
author      = {C. J. Lin},
title       = {Computational Complexity of Primal--Dual Path Following 
               Methods for Linear Semi--Definite Programming}, 
howpublished= {IOE 610 term project report},
year        = {1996},
address     = {Ann Arbor, MI 48109-2117},
institution = {Department of Industrial and Operations Engineering, 
	       University of Michigan}
}

@Article{CJL96a,
  author = 	 {Chih-Jen Lin and Soon-Yi Wu and Shu-Cherng Fang},
  title = 	 {On the parametric linear semi--infinite optimization},
  journal = 	 {Applied Mathematics Letter},
  year = 	 {1996},
  volume =	 {9},
  pages =	 {89--96}
}


@TechReport{CJL97a,
address     = {Argonne, Illinois},
author      = {Chih-Jen Lin and Jorge J. Mor\'e},
institution = {Mathematics and Computer Science Division, 
               Argonne National Laboratory},
title       = {Incomplete {C}holesky Factorizations with Limited Memory},
year        = {1997},
type        = {Preprint},
number      = {MCS-P682-0897},
note        = {To appear in SIAM Journal on  Scientific Computing}}
}


@TechReport{CJL97b,
address     = {Argonne, Illinois},
author      = {Chih-Jen Lin and Jorge J. Mor\'e},
institution = {Mathematics and Computer Science Division, 
               Argonne National Laboratory},
title       = {Newton's method for large-scale bound constrained problems},
year        = {1998},
type        = {Preprint},
note        = {Submitted to SIAM Journal on Optimization}
}



@InProceedings{CJL97c,
author      = {Chih-Jen Lin},
title       = {Preconditioning dense linear systems from
large-scale semidefinite programming problems}, 
  booktitle = 	 {Proceedings of the Fifth Copper Mountain conference
on iterative methods},
  year =	 {1998}
}
%  Second prize of the student paper competition.


@TechReport{CJL97d,
author      = {Chih-Jen Lin and Romesh Saigal},
address     = {Ann Arbor, MI 48109-2117},
institution = {Department of Industrial and Operations Engineering, 
	       University of Michigan},
title       = {On solving large-scale semidefinite programming
problems-- a case study of  quadratic assignment problem}, 
year        = {1997},
note        = {Submitted to {\em Comp. Optim. Appl.}}
}

@Article{CJL97e,
  author =	 {Shu-Cherng Fang and Soon-Yi Wu  and Chih-Jen Lin},
  title =	 {Relaxed cutting plane method for 
solving linear semi-infinite  programming problems},
  year =	 {1998},
  journal = 	 {Journal of 
Optimization Theory and Applications},
  volume =	 {99},
  pages =	 {759--779}
}


@article{LL07a,
author = {Liao, Lin and Patterson, Donald J. and Fox, Dieter and Kautz, Henry},
title = {Learning and inferring transportation routines},
journal = {Artificial Intelligence},
issue_date = {April, 2007},
volume = {171},
number = {5-6},
year = {2007},
issn = {0004-3702},
pages = {311--331},
numpages = {21},
url = {http://dx.doi.org/10.1016/j.artint.2007.01.006},
doi = {10.1016/j.artint.2007.01.006},
acmid = {1238288},
publisher = {Elsevier Science Publishers Ltd.},
address = {Essex, UK},
keywords = {Activity recognition, Hierarchical Markov model, Location tracking, Novelty detection, Rao--Blackwellized particle filters},
}

@PhdThesis{CJL98a,
  author = 	 {Chih-Jen Lin},
  title = 	 {Study in Large-Scale optimization},
  school = 	 {University of Michigan},
  year = 	 {1998},
  address =	 {Ann Arbor, Michigan}
}


@Article{CJL98b,
  author = 	 {Chih-Jen Lin and Soon-Yi Wu and Shu-Cherng Fang},
  title = 	 {An unconstrained convex programming approach for solving linear
semi-infinite programming problems},
  journal = 	 {SIAM Journal on Optimization},
  year = 	 {1998},
  volume =       {8}, 
  number =	 {2},
  page =         {443-456}
}



@Article{CJL99a,
  author = 	 {Chih-Jen Lin and Jorge J. Mor\'e},
  title = 	 {Incomplete {C}holesky Factorizations with Limited Memory},
  journal = 	 {SIAM Journal on Scientific Computing},
  year = 	 {1999},
  volume =	 {21},
  pages =	 {24--45}
}

@Article{CJL99b,
author      = {Chih-Jen Lin and Jorge J. Mor\'e},
title       = {Newton's method for large-scale bound constrained problems},
year        = {1999},
  journal = 	 {SIAM Journal on Optimization},
  volume =	 {9},
  pages =	 {1100--1127}
}
%  url = {http://www.mcs.anl.gov/~more/tron}

@Article{CJL99b-short,
author      = {Chih-Jen Lin and Jorge J. Mor\'e},
title       = {Newton's method for large-scale bound constrained problems},
year        = {1999},
  journal = 	 {SIAM J. Optim.},
  volume =	 {9},
  pages =	 {1100--1127}
}

@InProceedings{Lin99c,
  author = 	 {Chih-Jen Lin and
Nestor Michelena and Romesh Saigal},
  title = 	 {Topological fixture synthesis using semidefinite
programming},
  booktitle = 	 {Proceedings 
of the Third World Congress of Structural
and Multidisciplinary Optimization (WCSMO-3)},
  year =	 1999,
  month =	 {May 17-21}
}



@Article{CJL00a,
  author = 	 {Chih-Jen Lin and Romesh Saigal},
  title = 	 {An incomplete {C}holesky factorization for dense matrices},
  journal = 	 {BIT},
  year = 	 {2000},
  volume =	 {40},
  pages =	 {536--558}
}

@Article{CJL01a,
  author = 	 {Chih-Jen Lin},
  title = 	 {Formulations of Support Vector Machines: a Note from an
    Optimization Point of View},
  year = 	 {2001},
  journal  = {Neural Computation},
  volume =	 {13},
  pages = {307--317},
  number =	 {2}
}

@Article{CJL01b,
  author = 	 {Chih-Jen Lin},
  title = 	 {A formal analysis of stopping criteria of 
decomposition methods for support
vector machines
},
  journal = {IEEE Transactions on Neural Networks},
  volume={13},
  number={5},
  pages={1045--1052},
  year = 	 {2002},
  url={http://www.csie.ntu.edu.tw/~cjlin/papers/stop.ps.gz}
}

@Article{CJL01b-short,
  author = 	 {Chih-Jen Lin},
  title = 	 {A formal analysis of stopping criteria of 
decomposition methods for support
vector machines
},
  journal = {IEEE TNN},
  volume={13},
  number={5},
  pages={1045--1052},
  year = 	 {2002},
  url={http://www.csie.ntu.edu.tw/~cjlin/papers/stop.ps.gz}
}


@Article{CJL01c,
  author = 	 {Chih-Jen Lin},
  title = 	 {On the convergence 
of the decomposition method for 
 support vector machines},
  year = 	 {2001},
  journal = {IEEE Transactions on Neural Networks},
  volume = {12},
  number = {6},
  pages={1288--1298},
  url={http://www.csie.ntu.edu.tw/~cjlin/papers/conv.ps.gz}
}

@Article{CJL01d,
  author = 	 {Chih-Jen Lin},
  title = 	 {Asymptotic Convergence of an {SMO} Algorithm Without Any Assumptions},
  pages= {248--250},
  year = 	 {2002},
  volume={13},
  number={1},
  journal = {IEEE Transactions on Neural Networks},
  url={http://www.csie.ntu.edu.tw/~cjlin/papers/q2conv.pdf}
}



@TechReport{CJL01e,
  author = 	 {Chih-Jen Lin},
  title = 	 {Linear Convergence of a 
Decomposition Method for Support
Vector Machines},
  institution =  {Department of Computer Science,
National Taiwan University},
  year = 	 {2001},
  url={http://www.csie.ntu.edu.tw/~cjlin/papers/linearconv.pdf}
}




@TechReport{CJL04a,
  author = 	 {Chih-Jen Lin and Ruby C. Weng},
  title = 	 {Simple Probabilistic Predictions for Support Vector Regression},
  institution =  {Department of Computer Science, National Taiwan University},
  year = 	 {2004},
  OPTkey = 	 {},
  OPTtype = 	 {},
  OPTnumber = 	 {},
  OPTaddress = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {},
  url={http://www.csie.ntu.edu.tw/~cjlin/papers/svrprob.pdf}
}

@Book{CJL05a,
  author =	 {Chih-Jen Lin},
  ALTeditor = 	 {},
  title = 	 {A Guide to Support Vector Machines},
  publisher = 	 {},
  year = 	 {},
  OPTkey = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTaddress = 	 {},
  OPTedition = 	 {},
  OPTmonth = 	 {},
  note =	 {},
  OPTannote = 	 {}
}




@Article{CJL05b,
  author = 	 {Chih-Jen Lin},
  title = 	 {Projected Gradient Methods for Non-negative Matrix Factorization},
  year = 	 {2007},
  journal = 	 {Neural Computation},
  url =	 {http://www.csie.ntu.edu.tw/~cjlin/papers/pgradnmf.pdf},
  volume =	 {19},
  pages =	 {2756--2779},
  OPTkey = 	 {},
  OPTtype = 	 {},
  OPTnumber = 	 {},
  OPTaddress = 	 {},
  OPTmonth = 	 {},
  OPTannote = 	 {}
}


@Article{CJL05c,
  author = 	 {Chih-Jen Lin},
  title = 	 {On the Convergence of Multiplicative Update Algorithms for Non-negative Matrix Factorization},
  year = 	 {2007},
  url =	 {http://www.csie.ntu.edu.tw/~cjlin/papers/multconv.pdf},
  journal = {IEEE Transactions on Neural Networks},
  pages =	 {1589--1596},
  volume =	 {18},
  OPTkey = 	 {},
  OPTtype = 	 {},
  number =	 {6},
  OPTaddress = 	 {},
  OPTmonth = 	 {},
  OPTannote = 	 {}
}

@inproceedings{CJL07a,
  author    = {Chih-Jen Lin and Ruby C. Weng and S. Sathiya Keerthi},
  title     = {Trust region {N}ewton method for large-scale logistic
regression},
  booktitle = {Proceedings of the 24th International Conference on
               Machine Learning (ICML)},
  year      = {2007},
  note = {Software available at \url{http://www.csie.ntu.edu.tw/~cjlin/liblinear}}
}

@inproceedings{CJL07a-short,
  author    = {Chih-Jen Lin and Ruby C. Weng and S. Sathiya Keerthi},
  title     = {Trust region {N}ewton method for large-scale logistic
regression},
  booktitle = {ICML},
  year      = {2007}
}

@Article{CJL07b,
  author    = {Chih-Jen Lin and Ruby C. Weng and S. Sathiya Keerthi},
  title     = {Trust region {N}ewton method for large-scale logistic regression},
  year      = {2008},
  journal = 	 {Journal of Machine Learning Research},
  url =	 {http://www.csie.ntu.edu.tw/~cjlin/papers/logistic.pdf},
  OPTkey = 	 {},
  volume =	 {9},
  pages =	 {627--650},
  OPTmonth = 	 {},
  OPTannote = 	 {}
}
%  note = {Software available at \url{http://www.csie.ntu.edu.tw/~cjlin/liblinear}},


@Article{CJL07b-short,
  author    = {Chih-Jen Lin and Ruby C. Weng and S. Sathiya Keerthi},
  title     = {Trust region {N}ewton method for large-scale logistic
regression},
  year      = {2008},
  journal =      {JMLR},
  OPTkey =   {},
  volume =	 {9},
  pages =	 {627--650},
  OPTmonth =     {},
  OPTannote =    {}
}

@Article{CJL08a,
  author = 	 {Chih-Jen Lin and Stefano
Lucidi and Laura Palagi and Arnaldo Risi and Marco Sciandrone},
  title = 	 {Decomposition algorithm model for singly linearly constrained problems subject to lower and upper bounds},
  journal={Journal of Optimization Theory and Applications},
  year = 	 {2009},
  OPTkey = 	 {},
  volume =	 {141},
  OPTnumber = 	 {},
  pages =	 {107--126},
  OPTmonth = 	 {},
  OPTannote = 	 {}
}

@Article{CJL08a-short,
  author = 	 {Chih-Jen Lin and Stefano
Lucidi and Laura Palagi and Arnaldo Risi and Marco Sciandrone},
  title = 	 {Decomposition algorithm model for singly linearly constrained problems subject to lower and upper bounds},
  journal={J. Optim. Theory Appl.},
  year = 	 {2009},
  volume =	 {141},
  pages =	 {107--126}
}

@TechReport{HTL03a,
  author = 	 {Hsuan-Tien Lin and
 Chih-Jen Lin},
  title = 	 {A Study on Sigmoid Kernels for {SVM} and the Training
of non-{PSD} Kernels  by
{SMO}-type Methods},
  institution =  {Department of Computer Science,
National Taiwan University},
  year = 	 {2003},
  url =	 {http://www.csie.ntu.edu.tw/~cjlin/papers/tanh.pdf}
}
%  url={http://www.csie.ntu.edu.tw/\~cjlin/papers/tanh.pdf}


@Article{HTL03b,
  author = 	 {Hsuan-Tien Lin and
 Chih-Jen Lin and Ruby C. Weng},
  title = 	 {A note on {P}latt's probabilistic outputs for support vector machines},
  journal = {Machine Learning},
  year = 	 {2007},
  volume =	 {68},
  pages =	 {267--276},
  url={http://www.csie.ntu.edu.tw/~cjlin/papers/plattprob.pdf}
}

@Article{HTL08a,
  author = 	 {Hsuan-Tien Lin and Ling Li},
  title = 	 {Support Vector Machinery for Infinite Ensemble Learning},
  journal = 	 {Journal of Machine Learning Research},
  year = 	 {2008},
  volume =	 {9},
  pages =	 {285--312},
  OPTmonth = 	 {2}
}

@mastersthesis{HZL24a,
  author = {He-Zhe Lin},
  title = {Exploring Space Efficiency in a Tree-based Linear Model for Extreme Multi-label Classification},
  school = {Department of Computer Science and Information Engineering, National Taiwan University},
  year = {2024}
}

@inproceedings{HZL24b,
    title = "Exploring Space Efficiency in a Tree-based Linear Model for Extreme Multi-label Classification",
    author = "Lin, He-Zhe  and
      Liu, Cheng-Hung  and
      Lin, Chih-Jen",
    booktitle = "Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP)",
    year = "2024",
    url = {https://www.csie.ntu.edu.tw/~cjlin/papers/multilabel_tree_model_size/multilabel_tree_model_size.pdf}
}

@article{SWL08a,
  title={Particle swarm optimization for parameter determination and feature selection of support vector machines},
  author={Lin, Shih-Wei and Ying, Kuo-Ching and Chen, Shih-Chieh and Lee, Zne-Jung},
  journal={Expert Systems with Applications},
  volume={35},
  number={4},
  pages={1817--1824},
  year={2008}
}

@article{SWL08b,
  title={Parameter determination of support vector machine and feature selection using simulated annealing approach},
  author={Lin, Shih-Wei and Lee, Zne-Jung and Chen, Shih-Chieh and Tseng, Tsung-Yuan},
  journal={Applied Soft Computing},
  volume={8},
  number={4},
  pages={1505--1512},
  year={2008}
}


@InProceedings{JL12a,
  author = 	 {Jimmy Lin and Alek Kolcz},
  title = 	 {Large-Scale Machine Learning at {T}witter},
  OPTcrossref =  {},
  OPTkey = 	 {},
  booktitle =	 {Proceedings of the 2012 ACM SIGMOD International Conference on Management of Data (SIGMOD 2012)},
  pages =	 {793--804},
  year =	 {2012},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTaddress = 	 {},
  OPTmonth = 	 {},
  OPTorganization = {},
  OPTpublisher = {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}


@misc{JL12b,
  author    = {Jimmy Lin},
  title     = {Map{R}educe is Good Enough? If All You Have is a Hammer, Throw
               Away Everything That's Not a Nail!},
  year      = {2012},
  note={arXiv preprint arXiv:1209.2191}
}

@article{JL13b,
 author = {Lin, Jimmy and Ryaboy, Dmitriy},
 title = {Scaling Big Data Mining Infrastructure: The {T}witter Experience},
 journal = {SIGKDD Explorations Newsletter},
 volume = {14},
 number = {2},
 year = {2013},
 pages = {6--19}
}

@article{JL13b-short,
 author = {Lin, Jimmy and Ryaboy, Dmitriy},
 title = {Scaling Big Data Mining Infrastructure: The {T}witter Experience},
 journal = {SIGKDD Explor.},
 volume = {14},
 year = {2013},
 pages = {6--19}
}

@inproceedings{KL10a,
author = {Lin, Kaisen and Kansal, Aman and Lymberopoulos, Dimitrios and Zhao, Feng},
title = {Energy-accuracy trade-off for continuous mobile device location},
booktitle = {Proceedings of the 8th international conference on Mobile systems, applications, and services},
series = {MobiSys '10},
year = {2010},
isbn = {978-1-60558-985-5},
location = {San Francisco, California, USA},
pages = {285--298},
numpages = {14},
url = {http://doi.acm.org/10.1145/1814433.1814462},
doi = {10.1145/1814433.1814462},
acmid = {1814462},
publisher = {ACM},
address = {New York, NY, USA},
keywords = {GPS energy, continuous location, location-based applications},
}

@MastersThesis{KYL10a,
  author = 	 {Lin, Ken-Yi},
  title = 	 {Data Selection Techniques for Large-scale Rank{SVM}},
  school = 	 {Department of Computer Science and Information Engineering, National Taiwan University},
  year = 	 {2010}
}

@MastersThesis{KYL10a-short,
  author = 	 {Lin, Ken-Yi},
  title = 	 {Data Selection Techniques for Large-scale Rank{SVM}},
  school = 	 {National Taiwan University},
  year = 	 {2010}
}

@InProceedings{KPL11a,
  author = 	 {Keng-Pei Lin and Ming-Syan Chen},
  title = 	 {Efficient Kernel Approximation for Large-Scale
Support Vector Machine Classification},
  booktitle = 	 {Proceedings of the Eleventh SIAM International Conference on Data Mining},
  OPTcrossref =  {},
  OPTkey = 	 {},
  OPTpages = 	 {},
  year =	 {2011},
  pages =        {211--222},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTaddress = 	 {},
  OPTmonth = 	 {},
  OPTorganization = {},
  OPTpublisher = {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@Article{KML02a,
  author = 	 {Kuan-Min Lin and Chih-Jen Lin},
  title = 	 {A study on reduced support vector machines},
  year = 	 {2003},
  journal = 	 {IEEE Transactions on Neural Networks},
  volume =	 {14},
  number =	 {6},
  pages =	 {1449--1559},
  url={http://www.csie.ntu.edu.tw/~cjlin/papers/rsvmTEX.pdf}
}

@Article{KML02a-short,
  author = 	 {Kuan-Min Lin and Chih-Jen Lin},
  title = 	 {A study on reduced support vector machines},
  year = 	 {2003},
  journal = 	 {IEEE TNN},
  volume =	 {14},
  number =	 {6},
  pages =	 {1449--1559}
}


@MastersThesis{KML02b,
  author = 	 {Kuan-Min Lin},
  title = 	 {Reduction Techniques for Training Support Vector Machines},
  school = 	 {Department of Computer Science and Information Engineering, National Taiwan University},
  year = 	 {2002}
}



@InProceedings{LCL22a,
  author = 	 {Li-Chung Lin and Cheng-Hung Liu and Chih-Ming Chen
and Kai-Chin Hsu and I-Feng Wu and Ming-Feng Tsai and
	Chih-Jen Lin},
  title = 	 {On the use of unrealistic predictions in hundreds of papers evaluating graph representations},
  OPTcrossref =  {},
  OPTkey = 	 {},
  booktitle =	 {Proceedings of the 
Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI)},
  year =	 {2022},
  url = {https://www.csie.ntu.edu.tw/~cjlin/papers/multilabel-embedding/multilabel_embedding.pdf},  
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  pages =	 {7479--7487},
  OPTmonth = 	 {},
  OPTaddress = 	 {},
  OPTorganization = {},
  OPTpublisher = {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@article{SDL03a,
	title={Using unsupervised link discovery methods to find interesting facts and connections in a bibliography dataset},
	author={Shou-De Lin and Hans Chalupskiy},
	journal={ACM SIGKDD Explorations Newsletter},
	volume={5},
	number={2},
	pages={173--178},
	year={2003},
	publisher={ACM}
}

@inproceedings{SDL03b,
	title={Exploiting a search engine to develop more flexible Web agents},
	author={Shou-De Lin and Craig A. Knoblock},
	booktitle={Proceedings of the 2003 IEEE/WIC International Conference on Web Intelligence},
	pages={54},
	year={2003},
	organization={IEEE Computer Society}
}

@inproceedings{SDL03c,
	title={Unsupervised link discovery in multi-relational data via rarity analysis},
	author={Shou-De Lin and Hans Chalupskiy},
	year={2003},
        pages={171--178},
        booktitle={Proceedings of the Third IEEE International Conference on Data Mining}
}

@inproceedings{SDL04a,
	title={Interesting instance discovery in multi-relational data},
	author={Shou-De Lin},
	booktitle={Proceedings of the 19th National Conference on Artifical Intelligence},
	pages={991--992},
	year={2004},
	organization={AAAI Press}
}

@INPROCEEDINGS{SDL04b,
	author = {Shou-De Lin},
	title = {Issues of verification for unsupervised discovery systems},
	booktitle = {Proceedings of the Workshop on Link Analysis and Group Detection (LinkKDD)},
	year = {2004}
}

@article{SDL05a,
	title={SERGEANT: A framework for building more flexible web agents by exploiting a search engine},
	author={Shou-De Lin and Craig A. Knoblock},
	journal={Web Intelligence and Agent Systems},
	volume={3},
	number={1},
	pages={1--15},
	year={2005},
	publisher={IOS Press}
}

@PhdThesis{SDL06a,
  author = 	 {Shou-De Lin},
  title = 	 {Modelling, Searching and Explaining Interesting Instances in
  Multi-Relational Network},
  school = 	 {University of Southern California},
  year = 	 {2006}
}

@MastersThesis{SDL06b,
  author = 	 {Shou-De Lin},
  title = 	 {Generating natural language description for paths in the
  semantic network},
  school = 	 {University of Southern California},
  year = 	 {2006}
}

@article{SDL06c,
	title={Discovering the linear writing order of a two-dimensional ancient hieroglyphic script},
	author={Shou-De Lin and Kevin Knight},
	journal={Artificial intelligence},
	volume={170},
	number={4-5},
	pages={409--421},
	year={2006},
	publisher={Elsevier}
}

@article{SDL07a,
	title={Discovering and explaining abnormal nodes in semantic graphs},
	author={Shou-De Lin and Hans Chalupsky},
	journal={IEEE Transactions on Knowledge and Data Engineering},
        volume={20},
	pages={1039--1052},
	year={2007}
}

@inproceedings{SDL08a,
	title={A semantics-enhanced language model for unsupervised word sense disambiguation},
	author={Shou-De Lin and Karin Verspoor},
	journal={Proceedings of the 9th International Conference on 
Computational Linguistics and Intelligent Text Processing},
	pages={287--298},
	year={2008}
}

@InProceedings{WHL02a,
  author = 	 {Wei-Hao Lin and Alexander Hauptmann},
  title = 	 {News Video           
        Classification Using SVM-based Multimodal Classifiers and  
        Combination Strategies},
  booktitle = 	 {ACM Multimedia},
  year =	 {2002},
  address =	 {Juan Les Pins, France}
}



@InProceedings{YCL22a,
  author = 	 {Yu-Chen Lin and Si-An Chen and Jie-Jyun Liu and Chih-Jen Lin},
  title =    {Linear Classifier: An Often-Forgotten Baseline for Text Classification},
  booktitle =    {Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL)},
  year =         {2023},
  url = {https://www.csie.ntu.edu.tw/~cjlin/papers/text_classification_baseline/text_classification_baseline.pdf},
  note =         {Short paper},
  pages = {1876--1888}
}

@InProceedings{YCL22a-short,
  author = 	 {Yu-Chen Lin and Si-An Chen and Jie-Jyun Liu and Chih-Jen Lin },
  title =    {Linear Classifier: An Often-Forgotten Baseline for Text Classification},
  booktitle =    {ACL},
  year =         {2023}
}

@mastersthesis{YJL23a,
  author = {Yu-Jen Lin},
  title = {On the Thresholding Strategies for Rare Labels in Multi-label Classification},
  school = {Department of Computer Science and Information Engineering, National Taiwan University},
  year = {2023}
}

@inproceedings{YJL23b,
  title={On the thresholding strategy for infrequent labels in multi-label classification},
  author={Yu-Jen Lin and Chih-Jen Lin},
  booktitle={Proceedings of the 32nd ACM International Conference on Information and Knowledge Management (CIKM)},
  year = {2023},
  doi = {10.1145/3583780.3614996},
  url = {https://www.csie.ntu.edu.tw/~cjlin/papers/thresholding/smooth_acm.pdf},
 pages = {1441--1450}
}

@inproceedings{ZL17a,
author = "Lin, Zhouhan and Feng, Minwei and dos Santos, C{\'{\i}}cero Nogueira and Yu, Mo and Xiang, Bing and Zhou, Bowen and Bengio, Yoshua",
title = "A Structured Self-Attentive Sentence Embedding",
booktitle = "Proceedings of the Fifth International Conference on Learning Representations (ICLR)",
year = "2017",
}

@article{GL03a,
 author = {Linden, Greg and Smith, Brent and York, Jeremy},
 title = {Amazon.Com Recommendations: Item-to-Item Collaborative Filtering},
 journal = {IEEE Internet Computing},
 volume = {7},
 number = {1},
 year = {2003},
 pages = {76--80}
}

@article{GL03a-short,
 author = {Linden, Greg and Smith, Brent and York, Jeremy},
 title = {Amazon.Com Recommendations: Item-to-Item Collaborative Filtering},
 journal = {IEEE Internet Comput.},
 volume = {7},
 year = {2003},
 pages = {76--80}
}

@inproceedings{XL17a,
title={Model ensemble for click prediction in bing search ads},
author={Ling, Xiaoliang and Deng, Weiwei and Gu, Chen and Zhou, Hucheng and Li, Cui and Sun, Feng},
booktitle={Proceedings of the 26th International Conference on World Wide Web},
pages={689--698},
year={2017}
}

@inproceedings{XL17a-short,
title={Model ensemble for click prediction in bing search ads},
author={Ling, Xiaoliang and Deng, Weiwei and Gu, Chen and Zhou, Hucheng and Li, Cui and Sun, Feng},
booktitle={WWW},
year={2017}
}

@article{RAL06a,
  title={Infinite-$\sigma$ Limits For {T}ikhonov Regularization},
  author={Ross A. Lippert and Ryan M. Rifkin},
  journal={Journal of Machine Learning Research},
  volume={7},
  pages={855--876},
  year={2006},
  publisher={MIT Press Cambridge, MA, USA}
}

@article{RAL06a-short,
  title={Infinite-$\sigma$ Limits For {T}ikhonov Regularization},
  author={Ross A. Lippert and Ryan M. Rifkin},
  journal={JMLR},
  volume={7},
  pages={855--876},
  year={2006},
}

@article{ML19a,
 author = {Marco Lippi and Przemys{\l}aw Pa{\l}ka and Giuseppe Contissa and Francesca Lagioia and Hans-Wolfgang Micklitz and Giovanni Sartor and Paolo Torroni},
 title = {{CLAUDETTE}: an automated detector of potentially unfair clauses in online terms of service},
 journal = {Artificial Intelligence and Law},
 year = {2019},
 volume = {27},
 number = {2},
 pages = {117--139},
}

@inproceedings{ZCL14a,
  title={Optimal thresholding of classifiers to maximize {F1} measure},
  author={Lipton, Zachary C. and Elkan, Charles and Naryanaswamy, Balakrishnan},
  booktitle="Proceedings of the Joint European Conference on Machine Learning and Knowledge Discovery in Databases (ECML/PKDD)",
  pages={225--239},
  year={2014}
}

@InProceedings{NL04a,
  author =       {Nikolas List and Hans Ulrich Simon}, 
  title =        {A General Convergence Theorem for the Decomposition Method},
  booktitle =    {Proceedings of the 17th Annual Conference on Learning Theory},
  OPTcrossref =  {},
  OPTkey =       {},
  pages =        {363--377},
  year =         {2004},
  OPTnumber =    {},
  OPTaddress =   {},
  OPTorganization = {},
  OPTpublisher = {},
  OPTnote =      {},
  OPTannote =    {}
}

@InProceedings{NL05a,
  author = 	 {Nikolas List and Hans Ulrich Simon},
  title = 	 {General Polynomial Time Decomposition Algorithms},
  booktitle = 	 {Proceedings of the 18th Annual Conference on Computational Learning Theory},
  OPTcrossref =  {},
  OPTkey = 	 {},
  pages =	 {308--322},
  year =	 {2005},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTaddress = 	 {},
  OPTmonth = 	 {},
  OPTorganization = {},
  OPTpublisher = {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

%  editor =       {John Shawe-Taylor and Yoram Singer},
%  volume =       {3120},
%  series =       {Lecture Notes in Computer Science},

@article{NL07a,
  title={General polynomial time decomposition algorithms},
  author = 	 {Nikolas List and Hans Ulrich Simon},
  journal={Journal of Machine Learning Research},
  volume={8},
  pages={303--321},
  year={2007}
}



@InProceedings{NL09a,
  title={{SVM}-optimization and steepest-descent line search},
  author = 	 {Nikolas List and Hans Ulrich Simon},
  booktitle = 	 {Proceedings of the 22nd Annual Conference on Computational Learning Theory},
  year={2009}
}



@Book{RJAL02a,
  author =	 {Roderick J. A. Little and Donald B. Rubin},
  ALTeditor = 	 {},
  title = 	 {Statistical Analysis with Missing Data},
  publisher = 	 {Wiley-Interscience},
  year = 	 {2002},
  OPTkey = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTaddress = 	 {},
  edition =	 {Second},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@inproceedings{MJL88a,
author      = {M. J. Litzkow and M. Livny and M. W. Mutka},
booktitle   = {Proceedings of the 8th International Conference on
                  Distributed Computing Systems},
publisher   = {IEEE Computer Society Press},
address     = {Washington, District of Columbia},
pages       = {108--111},
title       = {Condor - {A} hunter of idle workstations},
year        = {1988},
}

@inproceedings{DCL17a,
 author = {Liu, David C. and Rogers, Stephanie and Shiau, Raymond and Kislyuk, Dmitry and Ma, Kevin C. and Zhong, Zhigang and Liu, Jenny and Jing, Yushi},
 title = {Related Pins at Pinterest: The Evolution of a Real-World Recommender System},
 booktitle = {Proceedings of the 26th International Conference on World Wide Web Companion (WWW)},
 year = {2017},
 pages = {583--592}
}

@inproceedings{DCL17a-short,
 author = {Liu, David C. and Rogers, Stephanie and Shiau, Raymond and Kislyuk, Dmitry and Ma, Kevin C. and Zhong, Zhigang and Liu, Jenny and Jing, Yushi},
 title = {Related Pins at Pinterest: The Evolution of a Real-World Recommender System},
 booktitle = {WWW},
 year = {2017}
}

@article{DCL89a,
  title={On the limited memory {BFGS} method for large scale optimization},
  author={Liu, Dong C. and Nocedal, Jorge},
  journal={Mathematical Programming},
  volume={45},
  number={1},
  pages={503--528},
  year={1989},
  publisher={Springer}
}

@article{DCL89a-short,
  title={On the limited memory {BFGS} method for large scale optimization},
  author={Liu, D. C. and Nocedal, J.},
  journal={Math. Program.},
  volume={45},
  number={1},
  pages={503--528},
  year={1989},
  publisher={Springer}
}

@inproceedings{HL20a,
author = "Liu, Han and Yuan, Caixia and Wang, Xiaojie",
editor = "Zhu, Xiaodan and Zhang, Min and Hong, Yu and He, Ruifang",
title = "Label-Wise Document Pre-training for Multi-label Text Classification",
booktitle = "Proceedings of Natural Language Processing and Chinese Computing (NLPCC)",
series = "Lecture Notes in Computer Science",
volume = "12430",
pages = "641--653",
year = "2020",
doi = "10.1007/978-3-030-60450-9\\_51",
}

@article{HL18a,
title={{CPLR}: collaborative pairwise learning to rank for personalized recommendation},
author={Liu, Hongzhi and Wu, Zhonghai and Zhang, Xing},
journal={Knowledge-Based Systems},
volume={148},
pages={31--40},
year={2018}
}


@article{JL15a,
  author={Liu, Ji and Wright, Stephen J and R{\'e}, Christopher and Bittorf, Victor and Sridhar, Srikrishna},
  title={An Asynchronous Parallel Stochastic Coordinate Descent Algorithm},
  journal={Journal of Machine Learning Research},
  volume={16},
  number={1},
  pages={285--322},
  year={2015}
}

@article{JL15a-short,
  author={Liu, Ji and Wright, Stephen J and R{\'e}, Christopher and Bittorf, Victor and Sridhar, Srikrishna},
  title={An Asynchronous Parallel Stochastic Coordinate Descent Algorithm},
  journal={JMLR},
  volume={16},
  year={2015}
}

@article{JL15b,
  author={Liu, Ji and Wright, Stephen J},
  title={Asynchronous Stochastic Coordinate Descent: Parallelism and Convergence Properties},
  journal={SIAM Journal on Optimization},
  volume={25},
  number={1},
  pages={351--376},
  year={2015}
}


@article{JL15b-short,
  author={Liu, Ji and Wright, Stephen J},
  title={Asynchronous Stochastic Coordinate Descent: Parallelism and Convergence Properties},
  journal = 	 {SIAM J. Optim.},  
  volume={25},
  year={2015}
}


@inproceedings{JL10a,
 author = {Liu, Jiahui and Dolan, Peter and Pedersen, Elin R{\o}nby},
 title = {Personalized news recommendation based on click behavior},
 booktitle = {Proceedings of the 15th international conference on Intelligent user interfaces},
 year = {2010},
 pages = {31--40}
} 

@inproceedings{JL13a,
author = {Liu, Jialu and Lei, Kin Hou and Liu, Jeffery Yufei and Wang, Chi and Han, Jiawei},
title = {Ranking-based Name Matching for Author Disambiguation in Bibliographic Data},
booktitle = {Proceedings of the KDD Cup 2013 Workshop},
year = {2013},
pages = {8:1--8:8},
publisher = {ACM},
} 


@InProceedings{JJL21a,
  author = 	 {Jie-Jyun Liu and Tsung-Han Yang and Si-An Chen and Chih-Jen Lin},
  title = 	 {Parameter Selection: Why We Should Pay More Attention to It},
  booktitle =    {Proceedings of the 59th Annual Meeting of the
Association of Computational Linguistics (ACL)},
  year =         {2021},
  pages =	 {825--830},  
  url = {https://www.csie.ntu.edu.tw/~cjlin/papers/parameter_selection/acl2021_parameter_selection.pdf},
  note =         {Short paper}
}

@InProceedings{JJL21a-short,
  author = 	 {Jie-Jyun Liu and Tsung-Han Yang and Si-An Chen and Chih-Jen Lin},
  title = 	 {Parameter Selection: Why We Should Pay More Attention to It},
  booktitle =    {ACL},
  year =         {2021}
}

@Article{JL95a,
  author = 	 {Jiming Liu},
  title = 	 {Sensitivity Analysis in Nonlinear Programs and Variational
Inequalities via Continuous Selections},
  journal = 	 {SIAM Journal on Control and Optimization},
  year = 	 {1995},
  volume =	 {33},
  number =	 {4},
  pages =	 {1040--1060}
}

@inproceedings{JL17a,
  title={Deep learning for extreme multi-label text classification},
  author={Liu, Jingzhou and Chang, Wei-Cheng and Wu, Yuexin and Yang, Yiming},
  booktitle={Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval},
  pages={115--124},
  year={2017}
}

@inproceedings{JL17a-short,
  title={Deep learning for extreme multi-label text classification},
  author={Liu, Jingzhou and Chang, Wei-Cheng and Wu, Yuexin and Yang, Yiming},
  booktitle={SIGIR},
  year={2017}
}

@inproceedings{JL09b,
  author = {Jun Liu and Jianhui Chen and Jieping Ye},
  title = {Large-scale Sparse Logistic Regression},
  booktitle = {Proceedings of The 15th ACM SIGKDD International Conference
on Knowledge Discovery and Data Mining},
  pages = {547--556},
  year = {2009}
}

@inproceedings{JL09d,
   title={Efficient Euclidean Projections in Linear Time},
   author={Jun Liu and Jieping Ye},
   booktitle = {Proceedings of the Twenty Sixth International Conference on
                Machine Learning (ICML)},
   year={2009},
}

@Article{LL18a,
AUTHOR = {Liu, Liu and Liu, Kaile and Cong, Zhenghai and Zhao, Jiali and Ji, Yefei and He, Jun},
TITLE = {Long Length Document Classification by Local Convolutional Feature Aggregation},
JOURNAL = {Algorithms},
VOLUME = {11},
YEAR = {2018},
NUMBER = {8},
DOI = {10.3390/a11080109}
}


@inproceedings{NNL10a,
  title={Unifying explicit and implicit feedback for collaborative filtering},
  author={Liu, Nathan N. and Xiang, Evan W. and Zhao, Min and Yang, Qiang},
  booktitle={Proceedings of the 19th ACM International Conference on Information and Knowledge Management (CIKM)},
  pages={1445--1448},
  year={2010}
}

@inproceedings{NNL10a-short,
  title={Unifying explicit and implicit feedback for collaborative filtering},
  author={Liu, Nathan N. and Xiang, Evan W. and Zhao, Min and Yang, Qiang},
  booktitle={CIKM},
  year={2010}
}

@inproceedings{QL18a,
title={Generalized Embedding Models for Knowledge Graph Mining},
author={Liu, Qiao and Wan, Rui and Yang, Xiaohui and Zeng, Yifu and Zhang, Haibin},
booktitle={Proceedings of the 14th International Workshop on Mining and Learning with Graphs (MLG)},
year={2018}
}

@ARTICLE{QL20a,
author={Liu, Qidong and Zhou, Xin and Long, Cheng and Zhang, Jie and Xu, Mingliang},
journal={IEEE Transactions on Computational Social Systems}, 
title={Learning Network Representations With Different Order Structural Information}, 
year={2020},
volume={7},
pages={907--914}
}

@ARTICLE{QL21a,
  author={Liu, Qidong and Long, Cheng and Zhang, Jie and Xu, Mingliang and Lv, Pei},
  journal={IEEE Transactions on Cybernetics}, 
  title={Tri{ATNE}: Tripartite Adversarial Training for Network Embeddings}, 
  year={2021},
  volume={},
  number={},
  pages={}
}

@MastersThesis{SL10b,
  author = 	 {Song Liu},
  title = 	 {Upscaling Key Machine Learning Algorithms},
  school = 	 {University of Bristol},
  year = 	 {2010},
  OPTkey = 	 {},
  OPTtype = 	 {},
  OPTaddress = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@incollection{TL05a,
title = {An Investigation of Practical Approximate Nearest Neighbor Algorithms},
author = {Ting Liu and Andrew W. Moore and Ke Yang and Alexander G. Gray},
booktitle = {Advances in Neural Information Processing Systems 17},
editor = {L.K. Saul and Y. Weiss and L. Bottou},
pages = {825--832},
year = {2005},
publisher = {MIT Press}
}

@ARTICLE{WL21a,
  author={Liu, Weiwei and Wang, Haobo and Shen, Xiaobo and Tsang, Ivor},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence}, 
  title={The Emerging Trends of Multi-Label Learning}, 
  year={2021},
  volume={},
  number={},
  pages={},
  note =	 {To appear}
}


@Article{XL04a,
  author = 	 {Xiaomei Liu and Lawrence O. Hall and Kevin W. Bowyer},
  title = 	 {Comments on ``{A Parallel Mixture of SVMs for Very Large Scale Problems}''},
  journal = 	 {Neural Computation},
  year = 	 {2004},
  OPTkey = 	 {},
  volume =	 {16},
  number =	 {7},
  pages =	 {1345--1351},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@inproceedings{XL18a,
  title={A Comparative Study of Network Embedding Based on Matrix Factorization},
  author={Liu, Xin and Kim, Kyoung-Sook},
  booktitle={International Conference on Data Mining and Big Data},
  pages={89--101},
  year={2018}
}



@InProceedings{YL22a,
  author = 	 {Yaxu Liu and Jui-Nan Yen and Bowen Yuan and Rundong Shi and Peng Yan and Chih-Jen Lin},
  title = 	 {Practical Counterfactual Policy Learning for Top-$K$ Recommendations},
  OPTcrossref =  {},
  OPTkey = 	 {},
  booktitle =	 {Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)},
  year =	 {2022},
  url = {https://www.csie.ntu.edu.tw/~cjlin/papers/counterfactual_topk/xcf.pdf},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTpages = 	 {},
  OPTmonth = 	 {},
  OPTaddress = 	 {},
  OPTorganization = {},
  OPTpublisher = {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}



@TechReport{YL24a,
  author = 	 {Yaxu Liu and Li-Chung Lin and Chih-Jen Lin},
  title = 	 {Examining the Bias of In-Batch Sampling in Similarity Learning with Two-Tower Models},
  institution =  {National Taiwan University},
  year = 	 {2024},
  OPTkey = 	 {},
  OPTtype = 	 {},
  OPTnumber = 	 {},
  OPTaddress = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@inproceedings{YL06a,
  title={Semi-supervised multi-label learning by constrained non-negative matrix factorization},
  author={Liu, Yi and Jin, Rong and Yang, Liu},
  booktitle={Proceedings of the Twenty-First National Conference on Artificial Intelligence (AAAI)},
  pages={421--426},
  year={2006}
}

@inbook{ZL20a,
author = {Liu, Zemin and Zhang, Wentao and Fang, Yuan and Zhang, Xinming and Hoi, Steven C.H.},
title = {Towards Locality-Aware Meta-Learning of Tail Node Embeddings on Networks},
year = {2020},
booktitle = {Proceedings of the 29th ACM International Conference on Information and Knowledge Management (CIKM)},
pages = {975--984}
}

@article{SL82a,
 author = {Lloyd, Stuart},
 title = {Least Squares Quantization in {PCM}},
 journal = {IEEE Transactions on Information Theory},
 volume = {28},
 number = {2},
 year = {1982},
 pages = {129--137},
}

@article{SL82a-short,
 author = {Lloyd, S.},
 title = {Least Squares Quantization in {PCM}},
 journal = {IEEE Trans. Inf. Theor.},
 volume = {28},
 year = {1982},
 pages = {129--137}
}

@article{HYL08a,
	title={Learning to improve area-under-FROC for imbalanced medical data classification using an ensemble method},
	author={Hung-Yi Lo and Chun-Min Chang and Tsung-Hsien Chiang and Cho-Yi Hsiao and Anta Huang
	and Tsung-Ting Kuo and Wei-Chi Lai and Ming-Han Yang and Jung-Jung Yeh and Chun-Chao Yen
	and Shou-De Lin},
	journal={ACM SIGKDD Explorations Newsletter},
	volume={10},
	number={2},
	pages={43--46},
	year={2008},
	publisher={ACM}
}

@InProceedings{HYL09a,
author = {Hung-Yi Lo and Kai-Wei Chang and Shang-Tse Chen and
Tsung-Hsien Chiang and Chun-Sung Ferng and Cho-Jui Hsieh and Yi-Kuang
Ko and Tsung-Ting Kuo and Hung-Che Lai and Ken-Yi Lin and Chia-Hsuan
Wang and Hsiang-Fu Yu and Chih-Jen Lin and Hsuan-Tien Lin and Shou-De
Lin},
title = {An Ensemble of Three Classifiers for {KDD} {C}up 2009: Expanded
Linear Model, Heterogeneous Boosting, and Selective Naive {B}ayes},
  booktitle = 	 {JMLR Workshop and Conference Proceedings: Proceedings of KDD-Cup 2009 competition},
  OPTcrossref =  {},
  OPTkey = 	 {},
  pages =	 {57--64},
  year =	 {2009},
  OPTeditor = 	 {},
  volume =	 {7},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTaddress = 	 {},
  OPTmonth = 	 {},
  OPTorganization = {},
  OPTpublisher = {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@inproceedings{HYL11a,
	title={Audio tag annotation and retrieval using tag count information},
	author={Hung-Yi Lo and Shou-De Lin and Hsin-Min Wang},
        booktitle={Proceedings of International Conference on Multimedia Modeling},
	year={2011}
}

@inproceedings{HYL11b,
	title={Cost-Sensitive Multi-Label Learning for Audio Tag Annotation and Retrieval},
	author={Hung-Yi Lo and Ju-Chiang Wang and Hsin-Min Wang and Shou-De Lin},
        booktitle={Proceedings of the International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
        year={2011}
}

@article{HL02a,
 author = {Huma Lodhi and Craig Saunders and John Shawe-Taylor and Nello Cristianini and Chris Watkins},
 title = {Text classification using string kernels},
 journal = {J. Mach. Learn. Res.},
 volume = {2},
 year = {2002},
 issn = {1533-7928},
 pages = {419--444},
 publisher = {MIT Press},
 }

@incollection{SL63a,
	Author = {{\L}ojasiewicz, Stanis{\l}aw},
	Booktitle = {Les \'Equations aus D\'eriv\'ees Partielles},
	Publisher = {\'Editions du centre National de la Recherche Scientifique},
	Title = {Une propri\'et\'e topologique des sous-ensembles analytiques r\'eels},
	Year = {1963}
}

@Book{CGL97a,
  author = 	 "Carl G. Looney",
  title = 	 "Pattern Recognition Using Neural Networks",
  publisher = 	 "Oxford University Press",
  year = 	 "1997"
}

@Article{GL07a,
  author = 	 {Ga\"{e}lle Loosli and St\'ephane Canu},
  title = 	 {Comments on the "{C}ore Vector Machines: Fast {SVM} Training on Very Large Data Sets"},
  journal = 	 {Journal of Machine Learning Research},
  year = 	 {2007},
  OPTkey = 	 {},
  volume =	 {8},
  OPTnumber = 	 {},
  pages =	 {291--301},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@incollection{GL07b,
  author = {Loosli, Ga\"{e}lle and Canu, St\'{e}phane and Bottou, L\'{e}on},
  title = {Training Invariant Support Vector Machines using Selective Sampling},
  pages = {301--320},
  editor = {Bottou, L\'{e}on and Chapelle, Olivier and {DeCoste}, Dennis and Weston, Jason},
  booktitle = {Large Scale Kernel Machines},
  publisher = {MIT Press},
  address = {Cambridge, MA.},
  year = {2007},
  url = {http://leon.bottou.org/papers/loosli-canu-bottou-2006},
}

@article{RL21a,
  title={Learning from eXtreme Bandit Feedback},
  author={Lopez, Romain and Dhillon, Inderjit and Jordan, Michael I.},
  booktitle={Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)},
  year={2021}
}

@inproceedings{IL19a,
  author    = {Ilya Loshchilov and 
               Frank Hutter},
  title     = {Decoupled Weight Decay Regularization},
  booktitle = {Proceedings of International Conference on Learning Representations},
  year      = {2019},
}

@inproceedings{JKL10a,
	title={What Can the Temporal Social Behavior Tell Us? An Estimation of Vertex-Betweenness Using Dynamic Social Information},
	author={Jing-Kai Lou and Shou-De Lin and Kuan-Ta Chen and Chin-Laung Lei},
	booktitle={2010 International Conference on Advances in Social Networks Analysis and Mining},
	pages={56--63},
	year={2010},
	organization={IEEE}
}

@article{JBL68a,
	author = {Julie Beth Lovins},
	title = {Development of a Stemming Algorithm},
	journal = {Mechanical Translation and Computational Linguistics},
	volume = {11},
	pages = {22--31},
	year = {1968},
}

@article{MAL21a,
title = {Network embedding from the line graph: Random walkers and boosted classification},
journal = {Pattern Recognition Letters},
volume = {143},
pages = {36--42},
year = {2021},
author = {Miguel Angel Lozano and Francisco Escolano and Manuel Curado and Edwin R. Hancock}
}

@inproceedings{HL10a,
 author = {Lu, Hong and Yang, Jun and Liu, Zhigang and Lane, Nicholas D. and Choudhury, Tanzeem and Campbell, Andrew T.},
 title = {The Jigsaw continuous sensing engine for mobile phone applications},
 booktitle = {Proceedings of the 8th ACM Conference on Embedded Networked Sensor Systems (SenSys)},
 year = {2010},
 pages = {71--84}
 }


@article{SL96a,
  author    = {Simon Lucas and A. Amiri},
  title     = {Statistical syntactic methods for High-performance {OCR}},
  journal={IEE Proceedings-Vision, Image and Signal Processing},
  volume={143},
  number={1},
  pages={23--30},
  year={1996}
}

 
@InProceedings{SL03a,
  author = 	 {Simon Lucas},
  title = 	 {Discriminative Training of the Scanning N-Tuple Classifier},
  booktitle = 	 {Proceedings of International Workshop on Artificial Neural Networks},
  year =	 {2003}
}

@inproceedings{ML18a,
author = {Lucic, Mario and Kurach, Karol and Michalski, Marcin and Gelly, Sylvain and Bousquet, Olivier},
booktitle = {Advances in Neural Information Processing Systems},
editor = {S. Bengio and H. Wallach and H. Larochelle and K. Grauman and N. Cesa-Bianchi and R. Garnett},
pages = {},
title = {Are {GANs} Created Equal? A Large-Scale Study},
volume = {31},
year = {2018}
}

@article{SL07a,
author = {Lucidi, Stefano and Palagi, Laura and Risi, Arnaldo and Sciandrone, Marco},
year = {2007},
pages = {217-234},
title = {A convergent decomposition algorithm for support vector machines},
volume = {38},
journal = {Computational Optimization and Applications}
}


@article{SL07a-short,
author = {Lucidi, Stefano and Palagi, Laura and Risi, Arnaldo and Sciandrone, Marco},
year = {2007},
pages = {217-234},
title = {A convergent decomposition algorithm for support vector machines},
volume = {38},
journal={Comput. Opt. App.}
}

@ARTICLE{SL09a, 
  author = {Stefano Lucidi and Laura Palagi and Arnaldo Risi and Marco Sciandrone},
  journal={IEEE Transactions on Neural Networks}, 
  title={A Convergent Hybrid Decomposition Algorithm Model for {SVM} Training}, 
  year={2009}, 
  volume={20}, 
  number={6}, 
  pages={1055--1060} 
}

@ARTICLE{SL09a-short, 
  author = {Stefano Lucidi and Laura Palagi and Arnaldo Risi and Marco Sciandrone},
  journal={IEEE TNN}, 
  title={A Convergent Hybrid Decomposition Algorithm Model for {SVM} Training}, 
  year={2009}, 
  volume={20}, 
  pages={1055--1060} 
}

@Book{DGL08a,
   author = {David G. Luenberger and Yinyu Ye},
   title = {Linear and Nonlinear Programming},
   publisher = {Springer},
   edition = {Third},
   year = {2008}
}

@article{HPL58a,
  title={The automatic creation of literature abstracts},
  author={Luhn, Hans Peter},
  journal={IBM Journal of Research and Development},
  volume={2},
  number={2},
  pages={159--165},
  year={1958}
}

@Article{LL98a,
  author =   {Ladislav Luk{\v s}an and Jan Vl{\v c}ek},
  title =    {A bundle-{N}ewton method for nonsmooth unconstrained
minimization},
  journal =    {Mathematical Programming: Series A},
  year =   1998,
  volume =   83,
  number =   3,
  pages =  {373--391}
}

@article{LL01a,
 author={Ladislav Luk{\v s}an and Jan Vl{\v c}ek},
 journal = {ACM Transactions on Mathematical Software (TOMS)},
 title = {Algorithm 811: {NDA}: algorithms for nondifferentiable optimization},
 volume = {27},
 number = {2},
 year = {2001},
 issn = {0098-3500},
 pages = {193--213},
 doi = {http://doi.acm.org/10.1145/383738.383740},
 publisher = {ACM Press}
 }

@book{RDL59a,
author      = {Lunce, R.~Duncan},
publisher   = {Wiley},
title       = {Individual Choice Behavior},
address     = {New York},
year        = {1959}
}

@article{CL80a,
  author = "C Lundsteen and J Phillip and E Granum",
  title = "Quantitative analysis of 6985 digitized trypsin {G}-banded human metaphase chromosomes",
  journal = "Clinical Genetics",
  volume = 18,
  pages = "355--370",
  year = 1980
}

@Article{AL67a,
  author = 	 {Lunts, A. and Brailovskiy,V.},
  title = 	 {Evaluation of attributes obtained in
statistical decision rules},
  journal = 	 {Engineerinh Cybernetics},
  year = 	 {1967},
  volume =	 {3},
  pages =	 {98--109}
}

@article{AL69a,
author={{Luntz, A. and Brailovsky, V.}},
title={On estimation of characters obtained in statistical procedure of
recognition},
journal={Technicheskaya Kibernetica 3},
year=1969}

@Article{ZQL92a,
  author = "Zhi-Quan Luo and Paul Tseng",
  title = "On the convergence of coordinate descent method for convex differentiable minimization",
  journal="Journal of Optimization Theory and
    Applications",
volume="72",
number="1",
pages="7--35",
  year = "1992" }

@Article{ZQL92a-short,
  author = "Z.-Q. Luo and Paul Tseng",
  title = "On the convergence of coordinate descent method for convex differentiable minimization",
  journal="J. Optim. Theory Appl.",
volume="72",
number="1",
pages="7--35",
  year = "1992" }

@Article{ZQL92a-vshort,
  author = "Z.-Q. Luo and Paul Tseng",
  title = "On the convergence of coordinate descent method for convex differentiable minimization",
  journal="JOTA",
volume="72",
number="1",
pages="7--35",
  year = "1992" }

@article{ZQL92b,
title={On the linear convergence of descent methods for convex
essentially smooth minimization},
author={Luo, Zhi-Quan and Tseng, Paul},
journal={SIAM Journal on Control and Optimization},
volume={30},
number={2},
pages={408--425},
year={1992}
}

@article{ZQL93a,
    title={Error bounds and convergence analysis of feasible descent methods: a general approach},
    author={Luo, Zhi-Quan and Tseng, Paul},
    year={1993},
    journal={Annals of Operations Research},
    volume={46},
    issue={1},
    pages={157-178}
}

@techreport {ZQL95a,
         author  = "Zhi-Quan Luo and J.F. Sturm and 
S. Zhang",
         title   = "Superlinear convergence of a symmetric primal-dual
   path following algorithm for semidefinite programming",
         institution = "Erasmus University Rotterdam",
         year    = "1996",
         address  = "The Netherlands",
         note = {To appear in {\em SIAM J. Optim.}}
     }


@Article{IJL92a,
  author = 	 {Lustig, I. J. and  Marsten, R. and Shanno, D. F.},
  title = 	 {On implementing Mehrotra's predictor-corrector interior point method for linear programming},
  journal = 	 {SIAM Journal on Optimization},
  year = 	 {1992},
  volume =	 {2},
  number =	 {3},
  pages =	 {435--449}
}

@INPROCEEDINGS{AL19a,
  author={Lutov, Artem and Yang, Dingqi and Cudré-Mauroux, Philippe},
  booktitle={Proceedings of the 2019 IEEE International Conference on Big Data}, 
  title={Bridging the Gap between Community and Node Representations: Graph Embedding via Community Detection}, 
  year={2019},
  pages={2681--2690}
}

@article{UVL07a,
 author = {Ulrike von Luxburg},
 title = {A tutorial on spectral clustering},
 journal = {Statistics and Computing},
 volume = {17},
 number = {4},
 year = {2007},
 pages = {395--416}
}

@inproceedings{QL21b,
author = {Lv, Qingsong and Ding, Ming and Liu, Qiang and Chen, Yuxiang and Feng, Wenzheng and He, Siming and Zhou, Chang and Jiang, Jianguo and Dong, Yuxiao and Tang, Jie},
title = {Are We Really Making Much Progress? Revisiting, Benchmarking and Refining Heterogeneous Graph Neural Networks},
year = {2021},
booktitle = {Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)},
pages = {1150--1160}
}

@InProceedings{SL02a,
  author = 	 {S. Lyu and H. Farid },
  title = 	 {Detecting Hidden Messages Using Higher-Order Statistics and Support Vector Machines 
},
  booktitle = 	 {5th International Workshop on Information Hiding},
  address =	 {Noordwijkerhout, The Netherlands},
 year={2002}
}

@article{CM16a,
  title={Distributed Inexact Damped {N}ewton Method: data Partitioning and Load-Balancing},
  author={Ma, Chenxin and Tak{\'a}{\v{c}}, Martin},
  journal={arXiv preprint arXiv:1603.05191},
  year={2016}
}

@article{CM16a-short,
  title={Distributed Inexact Damped {N}ewton Method: data Partitioning and Load-Balancing},
  author={Ma, Chenxin and Tak{\'a}{\v{c}}, Martin},
  journal={arXiv},
  year={2016}
}

@MastersThesis{CCM08a,
  school = 	 {National Taiwan University},
         author = {Chih-Chao Ma},
         title = {Large-scale Collaborative Filtering Algorithms},
         year = {2008},
         url = {http://www.csie.ntu.edu.tw/~r95007/thesis/svdnetflix/thesis.pdf}
 }

@InProceedings{HM11a,
  title   = {Recommender systems with social regularization},
  author  = {Ma, Hao and Zhou, Dengyong and Liu, Chao and Lyu, Michael
      R. and King, Irwin},
  booktitle = {Proceedings of the fourth ACM international conference on
      Web search and data mining},
  pages   = {287--296},
  year    = {2011}
}

@InProceedings{HM11a-short,
  title   = {Recommender systems with social regularization},
  author  = {Ma, Hao and Zhou, Dengyong and Liu, Chao and Lyu, Michael
      R. and King, Irwin},
  booktitle = {WSDM},
  year    = {2011}
}

@inproceedings{JM19a,
  title={Disentangled graph convolutional networks},
  author={Ma, Jianxin and Cui, Peng and Kuang, Kun and Wang, Xin and Zhu, Wenwu},
  booktitle={Proceedings of the 36th International Conference on Machine Learning (ICML)},
  pages={4212--4221},
  year={2019}
}

@inproceedings{JM20a,
title={Off-policy Learning in Two-stage Recommender Systems},
author={Ma, Jiaqi and Zhao, Zhe and Yi, Xinyang and Yang, Ji and Chen, Minmin and Tang, Jiaxi and Hong, Lichan and Chi, Ed H.},
booktitle={Proceedings of The Web Conference},
pages={463--473},
year={2020}
}

@inproceedings{JM20a-short,
title={Off-policy Learning in Two-stage Recommender Systems},
author={Ma, Jiaqi and Zhao, Zhe and Yi, Xinyang and Yang, Ji and Chen, Minmin and Tang, Jiaxi and Hong, Lichan and Chi, Ed H},
booktitle={WWW},
year={2020}
}

@inproceedings{JM09a,
   title={Identifying Suspicious {URL}s: An Application of Large-Scale Online Learning },
   author={Justin Ma and Lawrence K. Saul and Stefan Savage and Geoffrey M. Voelker},
   booktitle = {Proceedings of the Twenty Sixth International Conference on
                Machine Learning (ICML)},
   pages={681--688},
   year={2009}
}


@InProceedings{LM20a,
  author = 	 {Linjian Ma and Gabe Montague and Jiayu Ye and
Zhewei Yao and Amir Gholami and Kurt Keutzer and Michael W. Mahoney},
  title = 	 {Inefficiency of {K-FAC} for Large Batch Size Training},
  OPTcrossref =  {},
  OPTkey = 	 {},
  booktitle = {Proceedings of the Thirty-Fourth AAAI Conference on
Artificial Intelligence},
  year =	 {2020},
  OPTyear = 	 {},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTpages = 	 {},
  OPTmonth = 	 {},
  OPTaddress = 	 {},
  OPTorganization = {},
  OPTpublisher = {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@InProceedings{ALM11a,
  author    = {Maas, Andrew L.  and  Daly, Raymond E.  and  Pham, Peter T.  and  Huang, Dan  and  Ng, Andrew Y.  and  Potts, Christopher},
  title     = {Learning Word Vectors for Sentiment Analysis},
  booktitle = {Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies},
  year      = {2011},
  pages     = {142--150},
}

@phdthesis{DM16a,
  title={Modeling, inference and optimization with composable differentiable procedures},
  author={Maclaurin, Dougal},
  year={2016},
  school={Havard, University}
}

@article{DJCM92,
   author = "D. J. C. Mac{K}ay",
   title = "A practical {B}ayesian framework for backpropagation networks",
   journal = "Neural Computation",
   volume = "4(3)",
   pages = "448--472",
   year = "1992"
}

@Article{MCM77a,
  author =       "M. C. Mackey and L. Glass",
  title =        "Oscillation and chaos in physiological control
                 systems",
  journal =      "Science",
  volume =       "197",
  pages =        "287--289",
  year =         "1977",
  CODEN =        "SCIEAS",
  ISSN =         "0036-8075",
  alias =        "mackey77",
}

@inproceedings{JM67a,
  title={Some methods for classification and analysis of multivariate observations},
  author={MacQueen, James},
  booktitle={Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability},
  pages={281--297},
  year={1967}
}

@article{SAM07a,
  title={Classification in networked data: A toolkit and a univariate case study.},
  author={Macskassy, Sofus A. and Provost, Foster},
  journal={Journal of Machine Learning Research},
  volume={8},
  pages   = {935-983},
  year={2007}
}

@inproceedings{PM19a,
title = "On Model Stability as a Function of Random Seed",
author = "Madhyastha, Pranava  and
  Jain, Rishabh",
editor = "Bansal, Mohit  and
  Villavicencio, Aline",
booktitle = "Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)",
year = "2019",
doi = "10.18653/v1/K19-1087",
pages = "929--939",
}

@article{DM14a,
  title={A distributed block coordinate descent method for training l1 regularized linear classifiers},
  author={Mahajan, Dhruv and Keerthi, S. Sathiya and Sundararajan, Sellamanickam},
  journal={Journal of Machine Learning Research},
  year={2017},
  volume =	 {18},
  number =	 {91},
  pages={1--35}  
}

@article{DM14a-short,
  title={A distributed block coordinate descent method for training l1 regularized linear classifiers},
  author={Mahajan, Dhruv and Keerthi, S. Sathiya and Sundararajan, Sellamanickam},
  journal={JMLR},
  year={2017}
}

@techreport{AM07a,
	author = {Aigars Mahinovs and Ashutosh Tiwari},
	title = {Text Classification Method Review},
	publisher = {Cranfield University, UK.},
	year = {2007}
}

@InProceedings{RM02a,
  title={A comparison of algorithms for maximum entropy parameter estimation},
  author={Malouf, Robert},
  pages={1--7},
  year={2002},
  publisher={Association for Computational Linguistics},
  booktitle = 	 {Proceedings of the 6th conference on Natural language learning},
  OPTcrossref =  {},
  OPTkey = 	 {},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTaddress = 	 {},
  OPTmonth = 	 {},
  OPTorganization = {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@InProceedings{RM02a-short,
  title={A comparison of algorithms for maximum entropy parameter estimation},
  author={Malouf, Robert},
  year={2002},
  booktitle = 	 {CONLL}
}



@Article{LMM01a,
  author = 	 {Larry M. Manevitz and Malik Yousef},
  title = 	 {One-Class {SVM}s for Document Classification},
  journal = 	 {Journal of Machine Learning Research},
  year = 	 {2001},
  OPTkey = 	 {},
  volume =	 {2},
  OPTnumber = 	 {},
  pages =	 {139--154},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}



@article{OLM87a,
  title={Lipschitz continuity of solutions of linear inequalities, programs and complementarity problems},
  author={Mangasarian, Olvi L. and Shiau, Tzong-Huei},
  journal={SIAM Journal on Control and Optimization},
  volume={25},
  number={3},
  pages={583--595},
  year={1987}
}

@Article{OLM99a,
  author = 	 {O. L. Mangasarian and D. R. Musicant},
  title = 	 {Successive overrelaxation for support vector machines},
  journal = 	 {IEEE Transactions on Neural Networks},
  year = 	 {1999},
  volume =	 {10},
  number =	 {5},
  pages =	 {1032--1037}
}

@Article{OLM99a-short,
  author =   {O. L. Mangasarian and D. R. Musicant},
  title =    {Successive overrelaxation for support vector machines},
  journal =      {IEEE Trans. Neural Networks},
  year =     {1999},
  volume =   {10},
  number =   {5},
  pages =    {1032--1037}
}

@article{OLM99b,
title={Arbitrary-norm separating plane},
author={Mangasarian, Olvi L.},
journal={Operations Research Letters},
volume={24},
number={1},
pages={15--23},
year={1999}
}


@article{OLM00a,
    author = "O. L. Mangasarian and David R. Musicant",
    title = "Lagrangian Support Vector Machines",
    journal = "Journal of Machine Learning Research",
    volume = "1",
    pages = "161--177",
    year = "2001"
}

@InProceedings{OLM00b,
  author = 	 {O. L. Mangasarian},
  title = 	 {Generalized Support Vector Machines},
  booktitle = 	 {Advances in Large Margin
               Classifiers},
  pages =	 {135--146},
  year =	 {2000},
  editor =	 {A. J. Smola, P. Bartlett,
               B. Sch\"{o}lkopf and D. Schuurmans},
  publisher =	 {MIT Press}
}

@InProceedings{OLM01a,
  author    = {Olvi L. Mangasarian and David R. Musicant},
  title     = {Active Support Vector Machine Classification},
  booktitle = {Advances in Neural Information Processing Systems 13},
  pages     = {577--583},
  year      = {2001},
  editor    = {Leen, Todd K. and Dietterich, Thomas G. and Tresp, Volker},
  publisher = {MIT Press}
}



@article{OLM02a,
  title={A Finite {N}ewton Method for Classification},
  author={Mangasarian, Olvi L.},
  journal={Optimization Methods and Software},
  volume={17},
  number={5},
  pages={913--929},
  year={2002},
  publisher={Taylor \& Francis}
}

@article{OLM02a-short,
  title={A Finite {N}ewton Method for Classification},
  author={Mangasarian, Olvi L.},
  journal={Optim. Methods Softw.},
  volume={17},
  number={5},
  pages={913--929},
  year={2002},
  publisher={Taylor \& Francis}
}
@Article{OLM06a,
        author = {Olvi L. Mangasarian},
        title = {Exact 1-Norm Support Vector Machines via Unconstrained Convex Differentiable Minimization},
        journal = {Journal of Machine Learning Research},
        volume = {7},
        pages = {1517--1530},
        year = {2006}
}

@incollection{GM09a,
  title = {Efficient Large-Scale Distributed Training of Conditional Maximum Entropy Models},
  author = {Gideon Mann and Ryan McDonald and Mehryar Mohri and Nathan Silberman and Dan Walker},
  booktitle = {Advances in Neural Information Processing Systems 22},
  editor = {Y. Bengio and D. Schuurmans and J. Lafferty and C. K. I. Williams and A. Culotta},
  pages = {1231--1239},
  year = {2009}
}

@incollection{GM09a-short,
  title = {Efficient Large-Scale Distributed Training of Conditional Maximum Entropy Models},
  author = {Gideon Mann and Ryan McDonald and Mehryar Mohri and Nathan Silberman and Dan Walker},
  booktitle = {NIPS},
  year = {2009}
}

@inproceedings{CM14a,
  author    = {Manning, Christopher D and 
               Surdeanu, Mihai and 
               Bauer, John and 
               Finkel, Jenny Rose and 
               Bethard, Steven and 
               McClosky, David},
  title     = {The {S}tanford {C}ore{NLP} natural language processing toolkit},
  booktitle = {Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics: System Demonstrations},
  pages     = {55--60},
  year      = {2014}
}

@inproceedings{TAM79,
author      = {T. A. Manteuffel},
title       = {Shifted incomplete {C}holesky factorization},
booktitle   = {Sparse Matrix Proceedings},
year        = {1979},
pages       = {41--61},
publisher   = {SIAM, Philadelphia}
}

@article{TAM80,
author      = {T. A. Manteuffel},
journal     = {Math. Comp.},
pages       = {307--327},
title       = {An incomplete factorization technique for 
               positive definite linear systems},
volume      = {34},
year        = {1980}
}

@article{BGM21a,
  title={What is an optimal value of k in k-fold cross-validation in discrete Bayesian network analysis?},
  author={Marcot, Bruce G. and Hanea, Anca M.},
  journal={Computational Statistics},
  volume={36},
  number={3},
  pages={2009--2031},
  year={2021}
}

@article{BGM21a-short,
  title={What is an optimal value of k in k-fold cross-validation in discrete Bayesian network analysis?},
  author={Marcot, Bruce G. and Hanea, Anca M.},
  journal={Computational Statistics},
  year={2021}
}

@article{CCM19a,
  title={A review of automatic differentiation and its efficient implementation},
  author={Charles C. Margossian},
  journal={Wiley interdisciplinary reviews: data mining and knowledge discovery},
  volume={9},
  number={4},
  pages={e1305},
  year={2019}
}

@inproceedings{BMM09a,
 author = {Marlin, Benjamin M. and Zemel, Richard S.},
 title = {Collaborative Prediction and Ranking with Non-random Missing Data},
 booktitle = {Proceedings of the Third ACM Conference on Recommender Systems},
 year = {2009},
 pages = {5--12}
}

@inproceedings{BMM09a-short,
 author = {Marlin, Benjamin M. and Zemel, Richard S.},
 title = {Collaborative Prediction and Ranking with Non-random Missing Data},
 booktitle = {RecSys},
 year = {2009}
}

@inproceedings{BMM12a,
 author = {Marlin, Benjamin M. and Zemel, Richard S. and Roweis, Sam and Slaney, Malcolm},
 title = {Collaborative Filtering and the Missing at Random Assumption},
 booktitle = {Proceedings of the Twenty-Third Conference on Uncertainty in Artificial Intelligence},
 year = {2007},
 pages = {267--275}
} 

@inproceedings{BMM12a-short,
 author = {Marlin, Benjamin M. and Zemel, Richard S. and Roweis, Sam and Slaney, Malcolm},
 title = {Collaborative Filtering and the Missing at Random Assumption},
 booktitle = {UAI},
 year = {2007}
} 

@article{DWM63a,
   title={An algorithm for least-squares estimation of nonlinear parameters},
   author={Marquardt, Donald W.},
   journal={Journal of the Society for Industrial and Applied Mathematics},
   volume={11},
   number={2},
   pages={431--441},
   year={1963}
}

@article{JM95a,
  title={Inexact Newton methods for solving nonsmooth equations},
  author={Mart{\'\i}nez, Jos{\'e} Mario and Qi, Liqun},
  journal={Journal of Computational and Applied Mathematics},
  volume={60},
  number={1-2},
  pages={127--145},
  year={1995}
}

@article{JM95a-short,
  title={Inexact Newton methods for solving nonsmooth equations},
  author={Mart{\'\i}nez, Jos{\'e} Mario and Qi, Liqun},
  journal={J. Comput. Appl. Math.},  
  volume={60},
  pages={127--145},
  year={1995}
}


@InProceedings{MM10c,
  author = 	 {Michele Martone and Salvatore Filippone and Salvatore Tucci and Marcin Paprzycki},
  title = 	 {Assembling Recursively Stored Sparse Matrices},
  OPTcrossref =  {},
  OPTkey = 	 {},
  booktitle =	 {Proceedings of the International Multiconference on
Computer Science and Information Technology},
  year =	 {2010},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  pages =	 {317--325},
  OPTmonth = 	 {},
  OPTaddress = 	 {},
  OPTorganization = {},
  OPTpublisher = {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@InProceedings{MM10c-short,
  author = 	 {Michele Martone and Salvatore Filippone and Salvatore Tucci and Marcin Paprzycki},
  title = 	 {Assembling Recursively Stored Sparse Matrices},
  booktitle =	 {IMCSIT},
  year =	 {2010}
}

@inproceedings{MM10b,
  title={Utilizing Recursive Storage in Sparse Matrix-Vector Multiplication-Preliminary Considerations},
  author={Martone, Michele and Filippone, Salvatore and Tucci, Salvatore and Paprzycki, Marcin and Ganzha, Maria},
  booktitle={Proceedings of the ISCA 25th International Conference on Computers and Their
Applications},
  pages={300--305},
  year={2010}
}

@inproceedings{MM10b-short,
  title={Utilizing Recursive Storage in Sparse Matrix-Vector Multiplication-Preliminary Considerations},
  author={Martone, Michele and Filippone, Salvatore and Tucci, Salvatore and Paprzycki, Marcin and Ganzha, Maria},
  booktitle={CATA},
  year={2010}
}


@article{MM14a,
  title={Efficient multithreaded untransposed, transposed or symmetric sparse matrix--vector multiplication with the Recursive Sparse Blocks format},
  author={Martone, Michele},
  journal={Parallel Computing},
  volume={40},
  pages={251--270},
  year={2014}
}

@article{MM14a-short,
  title={Efficient multithreaded untransposed, transposed or symmetric sparse matrix--vector multiplication with the Recursive Sparse Blocks format},
  author={Martone, Michele},
  journal={Parallel Comput.},
  volume={40},
  pages={251--270},
  year={2014}
}



@article{MPM93a,
	author={Mitchell P. Marcus and Beatrice Santorini and Mary Ann Marcinkiewicz},
	title={Building a {L}arge {A}nnotated {C}orpus of {E}nglish: The
{P}enn {T}reebank},
	journal = {Computational Linguistics},
	volume={19},
	year={1993},
	pages={313--330}
}



@book{JIM95a,
author      = {John I. Marden},
publisher   = {Chapman \& Hall},
title       = {Analyzing and Modeling Rank Data},
address     = {London},
year        = {1995}
}

@misc{BM04a,
        author = "B. Marlin",
        title = "Collaborative filtering: A machine learning perspective",
        text = "B. Marlin. Collaborative filtering: A machine learning perspective. Master's thesis, University of Toronto, 2004.",
        year = "2004",
}

@article{MM61a,
  title={{Automatic Indexing: An Experimental Inquiry}},
  author={Maron, ME},
  journal={Journal of the ACM (JACM)},
  volume={8},
  number={3},
  pages={404--417},
  year={1961},
  publisher={ACM Press New York, NY, USA}
}

@inproceedings{JM10a,
  title={Deep learning via {H}essian-free optimization},
  author={Martens, James},
  booktitle={Proceedings of the 27th International Conference on Machine Learning (ICML)},
  year={2010}
}

@inproceedings{JM10a-short,
  title={Deep learning via {H}essian-free optimization},
  author={Martens, James},
  booktitle={ICML},
  year={2010}
}

@incollection{JM12a,
  title={Training deep and recurrent networks with {H}essian-free optimization},
  author={Martens, James and Sutskever, Ilya},
  booktitle={Neural Networks: Tricks of the Trade},
  pages={479--535},
  year={2012},
  publisher={Springer}
}



@InProceedings{JM15a,
  title = 	 {Optimizing Neural Networks with {K}ronecker-factored Approximate Curvature},
  author = 	 {James Martens and Roger Grosse},
  booktitle = 	 {Proceedings of the 32nd International Conference on Machine Learning},
  pages = 	 {2408--2417},
  year = 	 {2015}
}


@InProceedings{DRM02a,
  author = 	 {David R. Martin and Charless C. Fowlkes and Jitendra Malik},
  title = 	 {Learning to Detect Natural Image Boundaries Using Brightness and  Texture},
    booktitle = "Advances in Neural Information Processing Systems",
    volume = "14",
  year =	 {2002}
}

@MastersThesis{CM22a,
  author = {Carlos Marzal},
  title =  {Performance of Kernel Versus Linear One-Class {SVM}},
  school = {Department of Telecommunications Engineering, Universidad Polit{\'e}cnica de Madrid},
  year = {2022},
  month ={July}
}

@article{BM92a,
  title={{Classifying news stories using memory based reasoning}},
  author={Masand, B. and Linoff, G. and Waltz, D.},
  journal={Proceedings of the 15th annual international ACM SIGIR conference on Research and development in information retrieval},
  pages={59--65},
  year={1992},
  publisher={ACM Press New York, NY, USA}
}


@InProceedings{NM93a,
  author	= {N. Matic and I. Guyon and J. Denker and V. Vapnik},
  title		= {Writer adaptation for on-line handwritten character
		  recognition},
  booktitle	= {In Second International Conference on Pattern Recognition
		  and Document Analysis},
  pages		= {187--191},
  year		= {1993},
  editor	= {IEEE Computer Society Press},
  address	= {Tsukuba, Japan},
  url		= {http://www.clopinet.com/isabelle/Papers/adapt.ps},
  abstract	= {A TDNN without its last layer serves as a preprocessor to
		  an {SVM} classifier, that is retrained to peculiar writing
		  styles. This combination allows for fast writer dependent
		  learning of new letters and symbols.}
}

@book{JM06a,
	author = {Matou\v{s}ek, Ji\v{r}\'{\i} and G\"{a}rtner, Bernd},
	publisher = {Springer},
	title = {Understanding and Using Linear Programming},
	year = {2007}
}

@InProceedings{JM02a,
  author = 	 {Jochen Maydt and Rainer Lienhart},
  title = 	 {A Fast Method For Training Support Vector Machines With a Very Large Set of Linear Features},
  booktitle = 	 {Proceedings of IEEE ICME 2002},
  year =	 {2002},
  address =	 {Lousanne, Switzerland}
}

@InProceedings{EM99a,
    author = "Eddy Mayoraz and Ethem Alpaydin",
    title = "Support Vector Machines for Multi-class Classification",
    booktitle = "{IWANN} (2)",
    pages = "833--842",
    year = "1999",
    url = "http://citeseer.nj.nec.com/mayoraz98support.html"
}


@manual{MATLAB98,
title       = {MATLAB User Guide},
author      = {{The MathWorks, Inc.}},
year        = {1998},
address     = {Natick, MA 01760-1500}
}

@inproceedings{JM13a,
  title={Hidden factors and hidden topics: understanding rating dimensions with review text},
  author={McAuley, Julian and Leskovec, Jure},
  booktitle={Proceedings of the 7th ACM Conference on Recommender Systems},
  pages={165--172},
  year={2013}
}

@inproceedings{JM13a-short,
  title={Hidden factors and hidden topics: understanding rating dimensions with review text},
  author={McAuley, Julian and Leskovec, Jure},
  booktitle={RecSys},
  year={2013}
}

@inproceedings{AM98a,
title = {A comparison of event models for naive bayes text classification},
 author = {Andrew McCallum and  Kamal Nigam},
 year = {1998},
 booktitle = {Proceedings of the AAAI'98 Workshop on Learning for Text
categorization}
}

@inproceedings{AM99a,
title = "Multi-Label Text Classification with a Mixture Model Trained by
{EM}"
,author = "Andrew McCallum"
,year = 1999
,booktitle = "Proceedings of the AAAI'99 Workshop on Text Learning"
,keywords = "classification, multilabel, text, mixture model"
}

@INPROCEEDINGS{AM03a,
  author = {Andrew Mccallum and Wei Li},
  title = {Early Results for Named Entity Recognition with Conditional
Random Fields, Feature Induction and Web-Enhanced Lexicons},
  booktitle = {Seventh Conference on Natural Language Learning (CoNLL)},
  year = {2003}
}

@book{PM90a,
  title = {Generalized Linear Models},
  author = {P. McCullagh and J. A. Nelder},
  year = {1990},
  publisher = {CRC Press},
  edition = {2nd}
}

@inproceedings{AKM98a,
    author = "Andrew K. McCallum and Ronald Rosenfeld and Tom M. Mitchell and Andrew Y. Ng",
    title = "Improving text classification by shrinkage in a hierarchy of classes",
    booktitle = "Proceedings of {ICML}-98, 15th International Conference on Machine Learning",
    publisher = "Morgan Kaufmann Publishers, San Francisco, US",
    address = "Madison, US",
    editor = "Jude W. Shavlik",
    pages = "359--367",
    year = "1998",
    url = "citeseer.ist.psu.edu/mccallum98improving.html" 
}

@inproceedings{AKM98a-short,
    author = "Andrew K. McCallum and Ronald Rosenfeld and Tom M. Mitchell and Andrew Y. Ng",
    title = "Improving text classification by shrinkage in a hierarchy of classes",
    booktitle = "ICML",
    year = "1998"}


@Article{GPM72a,
  author = 	 {G. P. McCormick and R. A. Tapia},
  title = 	 {The gradient projection method under mild differentiability conditions},
  journal = 	 {SIAM Journal on Control},
  year = 	 {1972},
  OPTkey = 	 {},
  volume =	 {10},
  OPTnumber = 	 {},
  pages =	 {93--98},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@article{JM16a, 
 title={Diagnosing a disorder in a classification benchmark}, 
 author={James Mc{D}ermott and Richard S. Forsyth},
 journal={Pattern Recognition Letters}, 
 volume={73}, 
 pages={41-43}, 
 year={2016} 
} 

@InProceedings{RM06a,
     author = {Ryan Mc{D}onald and
               Fernando Pereira},
     title = {Online Learning of Approximate Dependency Parsing Algorithms},
     booktitle = {Proceedings of 11th Conference of the European  
Chapter of the Association for Computational Linguistics (EACL)},
     year = {2006},
     pages = {81--88}
}


@InProceedings{RM07a,
  title={Characterizing the errors of data-driven dependency parsing models},
  author={McDonald, Ryan and Nivre, Joakim},
  booktitle={Proceedings of the Joint Conferences on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL)},
  year={2007}
}

@inproceedings{RM10a,
  title={Distributed Training Strategies for the Structured Perceptron},
  author={McDonald, Ryan and Hall, Keith and Mann, Gideon},
  booktitle =    {Proceedings of the 48th Annual Meeting of the Association of Computational Linguistics (ACL)},
  pages={456--464},
  year={2010}
}

@inproceedings{RM10a-short,
  title={Distributed Training Strategies for the Structured Perceptron},
  author={McDonald, Ryan and Hall, Keith and Mann, Gideon},
  booktitle =    {ACL},
  year={2010}
}

@article{ACM69a,
author = {McKellar, A. C. and Coffman, E. G.},
title = {Organizing matrices and matrix operations for paged memory systems},
year = {1969},
volume = {12},
number = {3},
doi = {10.1145/362875.362879},
journal = {Communications of the ACM},
pages = {153--165}
}

@InProceedings{TM11a,
  author =   {Todd G. McKenzie and Chun-Sung Ferng and Yao-Nan
                  Chen, Chun-Liang Li and Cheng-Hao Tsai and Kuan-Wei
                  Wu and Ya-Hsuan Chang and Chung-Yi Li and Wei-Shih
                  Lin and Shu-Hao Yu and Chieh-Yen Lin and Po-Wei Wang
                  and Chia-Mau Ni and Wei-Lun Su and Tsung-Ting Kuo
                  and Chen-Tse Tsai and Po-Lung Chen and Rong-Bing
                  Chiu and Ku-Chun Chou and Yu-Cheng Chou and
                  Chien-Chih Wang and Chen-Hung Wu and Hsuan-Tien Lin
                  and Chih-Jen Lin and Shou-De Lin},
  title =  {Novel Models and Ensemble Techniques to Discriminate
                  Favorite Items from Unrated Ones for Personalized
                  Music Recommendation},
  booktitle = {ACM SIGKDD KDD-Cup WorkShop},
  year =   2011
}

@Book{GM92a,
 author = {Geoffrey J. McLachlan},
 title = {Discriminant Analysis and Statistical Pattern Recognition},
 publisher = {Wiley},
 year = {1992},
 address = {New York}
}

@inproceedings{HBM11a,
title = {Follow-the-Regularized-Leader and Mirror Descent: Equivalence Theorems and L1 Regularization},
author  = {H. Brendan Mc{M}ahan},
year  = 2011,
booktitle = {Proceedings of the 14th International Conference on Artificial Intelligence and Statistics (AISTATS)}
}

@inproceedings{HBM11a-short,
title = {Follow-the-Regularized-Leader and Mirror Descent: Equivalence Theorems and L1 Regularization},
author  = {H. Brendan Mc{M}ahan},
year  = 2011,
booktitle = {AISTATS}
}

@inproceedings{HBM13a,
title = {Ad Click Prediction: a View from the Trenches},
author  = {H. Brendan McMahan and Gary Holt and D. Sculley and Michael Young and Dietmar Ebner and Julian Grady and Lan Nie and Todd Phillips and Eugene Davydov and Daniel Golovin and Sharat Chikkerur and Dan Liu and Martin Wattenberg and Arnar Mar Hrafnkelsson and Tom Boulos and Jeremy Kubica},
year  = {2013},
booktitle = {Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)}
}

@inproceedings{HBM13a-short,
title = {Ad Click Prediction: a View from the Trenches},
author  = {H. Brendan McMahan and Gary Holt and D. Sculley and Michael Young and Dietmar Ebner and Julian Grady and Lan Nie and Todd Phillips and Eugene Davydov and Daniel Golovin and Sharat Chikkerur and Dan Liu and Martin Wattenberg and Arnar Mar Hrafnkelsson and Tom Boulos and Jeremy Kubica},
year  = {2013},
booktitle = {KDD}
}

@Article{JM98a,
  author =	 {J. McNames and J. A. K. Suykens and J. Vandewalle},
  title =	 {Winning Entry of the {K. U.} Leuven Time Series Prediction Competition},
 journal={International Journal of Bifurcation and Chaos},
volume={9},
number={8},
pages={1485--1500},
  year =	 {1999}
}


@InProceedings{NM89a,
  author =	 {N. Megiddo},
  editor =	 {N. Megiddo},
  title = 	 {Pathways to the optimal set in linear programming},
  booktitle = 	 {Progress in Mathematical Programming:         
 InteriorPoint Algorithms and Related Methods},
  pages =	 {131--158},
  year =	 1989,
  publisher =	 {Springer-Verlag},
  address =      {New York}
}


@Article{SM92a,
  author = 	 {S. Mehrotra},
  title = 	 {On the implementation of a (primal-dual) interior point method},
  journal = 	 {SIAM J. Optim.},
  year = 	 {1992},
  volume =	 {2},
  pages =	 {575--601}
}

@inproceedings{SM12a,
 author = {Matsushima, Shin and Vishwanathan, S.V.N. and Smola, Alexander J.},
 title = {Linear support vector machines via dual cached loops},
 booktitle = {Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining},
 year = {2012},
 pages = {177--185}
} 

@article{JMA77,
author      = {J. A. Meijerink and Van der Vorst, H. A.},
journal     = {Math. Comp.},
pages       = {148--162},
title       = {An iterative solution method for linear equations systems 
               of which the coefficient matrix is a symmetric {M}-matrix},
volume      = {31},
year        = {1977}
}


@article{JAM81,
author      = {J. A. Meijerink and Van der Vorst, H. A.},
journal     = {J. Comput. Phys.},
pages       = {134--155},
title       = {Guidelines for the usage of incomplete decompositions
                  in solving sets of linear equations as they occur in
                  practical problems},
volume      = {44},
year        = {1981}
}


		  
@InProceedings{MM03a,
  author = 	 {Marina Meila},
  title = 	 {Data Centering in Feature Space},
  booktitle = 	 {Proceedings of Ninth International Workshop on Artificial Intelligence and Statistics},
  year =	 {2003}
}

@article{SM11a,
  title={Laplacian Support Vector Machines Trained in the Primal},
  author={Melacci, Stefano and Belkin, Mikhail},
  journal={Journal of Machine Learning Research},
  volume={12},
  number={31},
  pages={1149--1184},
  year={2011}
}

@article{SM11a-short,
  title={Laplacian Support Vector Machines Trained in the Primal},
  author={Melacci, Stefano and Belkin, Mikhail},
  journal={JMLR},
  year={2011}
}

@techreport{RM06b,
author      = {Roland Memisevic},
institution = {Department of Computer Science,
University of Toronto},
title       = {Dual Optimization of Conditional Probability Models},
year        = {2006}
}

@incollection{LM10a,
author="Loza Menc{\'i}a, Eneldoand F{\"u}rnkranz, Johannes",
editor="Francesconi, Enrico and Montemagni, Simonetta and Peters, Wim
and Tiscornia, Daniela",
title="Efficient multilabel classification algorithms for large-scale problems in the legal domain",
bookTitle="Semantic Processing of Legal Texts: Where the Language of Law Meets the Law of Language",
year="2010",
publisher="Springer Berlin Heidelberg",
pages="192--215",
}

@incollection{LM10a-short,
author="Loza Menc{\'i}a, Eneldoand F{\"u}rnkranz, Johannes",
title="Efficient Multilabel Classification Algorithms for Large-Scale Problems in the Legal Domain",
bookTitle="Semantic Processing of Legal Texts: Where the Language of Law Meets the Law of Language",
year="2010",
publisher="Springer Berlin Heidelberg",
pages="192--215",
}

@article{XM16a,
author = {Xiangrui Meng and Joseph Bradley and Burak Yavuz
and Evan Sparks and Shivaram Venkataraman and Davies Liu and
Jeremy Freeman and DB Tsai and Manish Amde and Sean Owen and
Doris Xin and Reynold Xin and Michael J. Franklin and Reza
Zadeh and Matei Zaharia and Ameet Talwalkar},
title = {{ML}lib: Machine Learning in {A}pache {S}park},
journal = {Journal of Machine Learning Research},
year = {2016},
volume = {17},
number={1},
pages={1235--1241}
}

@article{XM16a-short,
author = {Xiangrui Meng and Joseph Bradley and Burak Yavuz
and Evan Sparks and Shivaram Venkataraman and Davies Liu and
Jeremy Freeman and DB Tsai and Manish Amde and Sean Owen and
Doris Xin and Reynold Xin and Michael J. Franklin and Reza
Zadeh and Matei Zaharia and Ameet Talwalkar},
title = {{ML}lib: Machine Learning in {A}pache {S}park},
journal = {JMLR},
year = {2016},
volume = {17},
pages={1235--1241}
}

@Article{JEM06a,
   author = 	 {Joshua E. Menke and Tony R. Martinez},
   title = 	 {A {B}radley-{T}erry artificial neural network model for individual ratings in group competitions},
   journal = 	 {Neural Computing and Applications},
   year = 	 {2008},
   OPTnumber =	 {},
   volume    = {17},
   pages     = {175--186}
}

@article{AKM10a,
  title={Predicting labels for dyadic data},
  author={Menon, Aditya Krishna and Elkan, Charles},
  journal={Data Mining and Knowledge Discovery},
  volume={21},
  pages={327--343},
  year={2010}
}

@inproceedings{AKM11a,
author = {Aditya Krishna Menon and Charles Elkan},
title = {Link Prediction via Matrix Factorization},
booktitle = {Proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases (ECML/PKDD)},
year = {2011},
pages = {437--452}
}

@inproceedings{AKM11a-short,
author = {Aditya Krishna Menon and Charles Elkan},
title = {Link Prediction via Matrix Factorization},
booktitle = {ECML/PKDD},
year = {2011}
}

@inproceedings{AKM11b,
 author = {Menon, Aditya Krishna and Chitrapura, Krishna-Prasad and Garg, Sachin and Agarwal, Deepak and Kota, Nagaraj},
 title = {Response Prediction Using Collaborative Filtering with Hierarchies and Side-information},
 booktitle = {Proceedings of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)},
 year = {2011},
 pages = {141--149}
}

@inproceedings{AKM11b-short,
 author = {Menon, Aditya Krishna and Chitrapura, Krishna-Prasad and Garg, Sachin and Agarwal, Deepak and Kota, Nagaraj},
 title = {Response Prediction Using Collaborative Filtering with Hierarchies and Side-information},
 booktitle = {KDD},
 year = {2011}
}


@article{JM09b,
title={Functions of positive and negative type, and their connection with
the theory of integral equations},
author={Mercer, James},
journal={Philosophical Transactions of the Royal Society of London. Series
A},
volume={209},
pages={415--446},
year={1909}
}


@inproceedings{DM99a,
  author = {Dimitris Meretakis and Beat W\"uthrich},
  booktitle = {SIGMOD},
  title = {Classification as Mining and Use of Labeled Itemsets},
  year = 1999
}


@article{NM53a,
  title={Equation of state calculations by fast computing machines},
  author={Metropolis, Nicholas and Rosenbluth, Arianna W. and Rosenbluth, Marshall N. and Teller, Augusta H. and Teller, Edward},
  journal={The Journal of Chemical Physics},
  volume={21},
  number={6},
  pages={1087--1092},
  year={1953}
}

@article{HWM97a,
  author    = {Hans-Werner Mewes and
               Kaj Albermann and
               Klaus Heumann and
               S. Lieb and
               Friedhelm Pfeiffer},
  title     = {{MIPS}: a database for protein sequences, homology data and
               yeast genome information.},
  journal   = {Nucleic Acids Research},
  volume    = {25},
  number    = {1},
  year      = {1997},
  pages     = {28--30},
  bibsource = {DBLP, http://dblp.uni-trier.de}
}


@incollection{HQM06a,
title={Mercer's theorem, feature maps, and smoothing},
author={Minh, Ha Quang and Niyogi, Partha and Yao, Yuan},
  booktitle = 	 {Proceedings of the Nineteenth Annual
     Workshop on Computational
     Learning Theory (COLT)},
pages={154--168},
year={2006}
}

@incollection{DM98a,
   author = {Dunja Mladeni\'c},
   title = {Feature subset selection in text-learning},
   booktitle = {10th European Conference on Machine Learning: ECML-98},
   keyword = {Computer Science},
   pages = {95-100},
   year = {1998}
}

@incollection{DM98a-short,
   author = {Dunja Mladeni\'c},
   title = {Feature subset selection in text-learning},
   booktitle = {ECML},
   pages = {95-100},
   year = {1998}
}

@Article{CAM86a,
  author = 	 {Charles A. Micchelli},
  title = 	 {Interpolation of scattered data: distance matrices and conditionally positive definite functions},
  journal = 	 {Constructive Approximation},
  year = 	 {1986},
  volume =	 {2},
  pages =	 {11--22}
}


@book{DM94a,
 editor = {Donald Michie and D. J. Spiegelhalter and C. C. Taylor and John Campbell},
 title = {Machine learning, neural and statistical classification},
 year = {1994},
 isbn = {0-13-106360-X},
 publisher = {Ellis Horwood},
 address = {Upper Saddle River, NJ, USA},
  note =	 {Data available at \url{http://archive.ics.uci.edu/ml/machine-learning-databases/statlog/}}
 }

@InProceedings{MI06a,
   author = {Mierswa, Ingo and Wurst, Michael and Klinkenberg, Ralf and Scholz, Martin and Euler, Timm},
   title = {{YALE}: Rapid Prototyping for Complex Data Mining Tasks},
   booktitle = {Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining (KDD)},
   year = {2006},
   pages = {935--940}
} 

% I think this method need semi-smooth, I am not sure about it
% I found a page but I can't not download this paper.
% http://www.iiasa.ac.at/cgi-bin/pubsrch?RR77003 
@Article{RM77b,
  author = 	 {R. Mifflin},
  title = 	 {An algorithm for constrained optimization with semismooth
functions},
  journal = 	 {Mathematics of Operations Research},
  year = 	 {1977},
  volume =	 {2},
  pages =	 {191--207}
}

@Article{RM77a,
  author = 	 {R. Mifflin},
  title = 	 {Semismooth and semiconvex functions in constrained
optimization},
  journal = 	 {SIAM Journal on Control and Optimization},
    year      = "1977",
    volume    = "15",
    pages     = "957--972",
    annote    = "{This is the first appearance in the literature of the
                  concept of a semismooth function.  Semismooth functions 
                  are closed under addition and composition, and also 
                  guarantee the local convergence of nonsmooth 
                  generalizations of Newton's method.}"

}


@inproceedings{BLM05a,
 author = {Boriana L. Milenova and Joseph S. Yarmus and Marcos M. Campos},
 title = {{SVM} in oracle database 10g: removing the barriers to widespread adoption of support vector machines},
 booktitle = {VLDB '05: Proceedings of the 31st international conference on Very large data bases},
 year = {2005},
 isbn = {1-59593-154-6},
 pages = {1152--1163},
 location = {Trondheim, Norway},
 publisher = {VLDB Endowment},
 }

@inproceedings{TM13a,
  title={Distributed representations of words and phrases and their compositionality},
  author={Mikolov, Tomas and Sutskever, Ilya and Chen, Kai and Corrado, Greg S and Dean, Jeff},
  booktitle={Advances in Neural Information Processing Systems (NIPS)},
  pages={3111--3119},
  year={2013},
  doi={10.5555/2999792.2999959}
}

@inproceedings{TM13a-short,
  title={Distributed representations of words and phrases and their compositionality},
  author={Mikolov, Tomas and Sutskever, Ilya and Chen, Kai and Corrado, Greg S and Dean, Jeff},
  booktitle={NIPS},
  pages={3111--3119},
  year={2013}
}

@inproceedings{TM13b,
  title={Efficient Estimation of Word Representations in Vector Space},
  author={Tomas Mikolov and Kai Chen and Gregory S. Corrado and Jeffrey Dean},
  booktitle={Proceedings of the International Conference on Learning Representations (ICLR)},
  year={2013}
}


@Article{GAM56,
   author = {George A. Miller},
   title = {The Magical Number Seven, Plus or Minus Two: Some Limits on Our Capacity for Processing Information},
   journal = {The Psychological Review},
   year = {1956},
   volume={63},
   pages={81--97}
}

@inproceedings{BNM03a,
        author = {Bradley N. Miller and Istvan Albert and Shyong K. Lam and Joseph A. Konstan and John Riedl},
        title = {MovieLens unplugged: experiences with an occasionally connected recommender system},
        booktitle = {IUI '03: Proceedings of the 8th international conference on Intelligent user interfaces},
        year = {2003},
        isbn = {1-58113-586-6},
        pages = {263--266},
        location = {Miami, Florida, USA},
        doi = {http://doi.acm.org/10.1145/604045.604094},
        publisher = {ACM},
        address = {New York, NY, USA},
}


@inproceedings{EM08a,
author = {Miluzzo, Emiliano and Lane, Nicholas D. and Fodor, Krist\'{o}f and Peterson, Ronald and Lu, Hong and Musolesi, Mirco and Eisenman, Shane B. and Zheng, Xiao and Campbell, Andrew T.},
title = {Sensing meets mobile social networks: the design, implementation and evaluation of the CenceMe application},
booktitle = {Proceedings of the 6th ACM conference on Embedded Network Sensor Systems},
series = {SenSys '08},
year = {2008},
isbn = {978-1-59593-990-6},
location = {Raleigh, NC, USA},
pages = {337--350},
url = {http://doi.acm.org/10.1145/1460412.1460445},
doi = {10.1145/1460412.1460445},
publisher = {ACM},
address = {New York, NY, USA},
}

@article{FM19a,
  title={Ten ways to fool the masses with machine learning},
  author={Minhas, Fayyaz and Asif, Amina and Ben-Hur, Asa},
  journal={arXiv preprint arXiv:1901.01686},
  year={2019}
}


@PhdThesis{TM01a,
   author = 	 {Thomas Minka},
   title = 	 {A family of algorithms for approximate {B}ayesian inference},
   school = 	 {MIT},
   year = 	 2001
}


@Misc{TPM03a,
 author =    {Thomas P. Minka},
 title =    {A comparison of numerical optimizers for logistic
regression},
 year =     {2003},
 note =     {\url{http://research.microsoft.com/en-us/um/people/minka/papers/logreg/minka-logreg.pdf}}
}


@Book{TMM97a,
  author = 	 "Tom M. Mitchell",
  title = 	 "Machine Learning",
  publisher = 	 "McGraw-Hill",
  year = 	 "1997"
}

@inproceedings{AM20a,
author = {Anasua Mitra and Priyesh Vijayan and Srinivasan Parthasarathy and Balaraman Ravindran},
title = {A Unified Non-Negative Matrix Factorization Framework for Semi Supervised Learning on Graphs},
booktitle = {Proceedings of the SIAM International Conference on Data Mining (SDM)},
pages = {487--495},
year = {2020}
}

@inproceedings{AM21a,
author = {Mitra, Anasua and Vijayan, Priyesh and Sanasam, Ranbir and Goswami, Diganta and Parthasarathy, Srinivasan and Ravindran, Balaraman},
title = {Semi-Supervised Deep Learning for Multiplex Networks},
booktitle = {Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)},
pages = {1234--1244}
}

@Article{SM94a,
  author = 	 {S. Mizuno},
  title = 	 {Polynomiality of infeasible-interior-point algorithm 
for linear programming},
  journal = 	 {Math. Programming},
  year = 	 {1994},
  volume =	 {67},
  pages =	 {109--120}
}

@Article{SM93a,
  author = 	 {S. Mizuno and M. ~J. Todd and ~Y. Ye},
  title = 	 {On adaptive step primal-dual interior-point algorithms for linear
programming},
  journal = 	 {Math. Oper. Res.},
  year = 	 {1993},
  volume =	 {18},
  pages =	 {964--981}
}

@InProceedings{JM74a,
author="Mo{\v{c}}kus, Jonas",
title="On {B}ayesian Methods for Seeking the Extremum",
booktitle = {Proceedings of the IFIP Technical Conference},
year="1974",
pages="400--404"
}

@inproceedings{AM11a,
 author={Mohan, Ananth and Chen, Zheng and Weinberger, Kilian},
 title={Web-search Ranking with Initialized Gradient Boosted Regression Trees},
 booktitle={JMLR Workshop and Conference Proceedings: Workshop on Yahoo! Learning to Rank Challenge},
 volume={14},
 pages={77--89},
 year={2011}
}

@inproceedings{YM08a,
         author = {Yvonne Moh and Joachim M. Buhmann},
         booktitle = {Proceedings of The International Society for
                 Music Information Retrieval (ISMIR)},
         pages = {167--172},
         title = {Kernel Expansion for Online Preference Tracking},
         year = {2008}
}

@inproceedings{SM18a,
title = "{S}em{E}val-2018 Task 1: Affect in Tweets",
author = "Mohammad, Saif  and
Bravo-Marquez, Felipe  and
Salameh, Mohammad  and
Kiritchenko, Svetlana",
editor = "Apidianaki, Marianna  and
Mohammad, Saif M.  and
May, Jonathan  and
Shutova, Ekaterina  and
Bethard, Steven  and
Carpuat, Marine",
booktitle = "Proceedings of the Twelfth International Workshop on Semantic Evaluation",
year = "2018",
doi = "10.18653/v1/S18-1001",
pages = "1--17",
}

@Article{MM02,
  author = 	 {Michinari Momma and Kristin P. Bennett},
  title = 	 {A Pattern Search Method for Model Selection of Support
Vector Regression},
  journal = 	 {Proceedings of SIAM Conference on Data Mining},
  year = 	 2002
}


@ONLINE{MS13a,
author = {{Monsoon Solution Inc.}},
title = {Power Monitor},
howpublished = {\url{http://www.msoon.com/}}
}

@inproceedings{AMR06a,
  title={Selection Strategies for Multi-label Text Categorization},
  author={Montejo-R{\'a}ez, Arturo and Ure\~na{-}L{\'o}pez, Luis Alfonso},
  booktitle="Proceedings of International Conference on Natural Language Processing (FinTAL)",
  pages={585--592},
  year={2006}
}

@article{JM89a,
    author = "J. Moody and C. J. Darken",
    title = "Fast learning in networks of locally--tuned processing units",
    journal = "Neural Computation",
    volume = "1",
    publisher = "MIT Press",
    pages = "281--293",
    year = "1989"
}


@Article{RDCM97,
  author = 	 {R. D. C. Monteiro},
  title = 	 {Primal-Dual Path Following Algorithms for Semidefinite Programming},
  year = 	 {1997},
  journal =      {SIAM J. Optim.},
  volume      = {7},
  pages       = {663--678}
}



@TechReport{RDCM96b,
  author = 	 {R. D. C. Monteiro},
  title = 	 {Polynomial convergence of primal-dual algorithms for
semidefinite programming based on {M}onteiro and {Z}hang
family of directions},
  institution =  {School of Industrial and Systems
Engineering, Georgia Institute of Technology},
  year = 	 {1996},
  type =	 {manuscript},
  address =	 {Atlanta, GA}
}

@article {RDCM97a,
         author  = "R.D.C. Monteiro and Y. Zanjacomo",
         title   = "A Note on the existence of the
{A}lizadeh-{H}aeberly-{O}verton
       Direction for Semidefinite Programming",
         journal = "Math. Programming",
         year    = "1997",
         volume = "78",
         pages = "393--401",
     ISSN = {0025-5610}
     }

@techreport {RDCM96a,
         author  = "R. D. C. Monteiro and Y. Zhang",
         title   = "A unified analysis for a class of 
path-following primal-dual interior-point algorithms for
semidefinite programming",
         institution = "Georgia Tech.",
         year    = "1996",
         address  = "Atlanta, GA",
         note = {To appear in {\em Math. Programming}}
     }

@Misc{RDCM98a,
  author = 	 {R. D. C. Monteiro and R. Saigal and M. J. Todd},
  title = 	 {Path-following methods for semidefinite programming},
  year = 	 {1998},
  type =	 {manuscript}
}


@InProceedings{JJM78a,
author      = {J. J. Mor\'e},
  title = 	 {The {L}evenberg-{M}arquardt algorithm: Implementation and theory},
  booktitle = 	 {Numerical Analysis},
  pages =	 {105--116},
  year =	 {1978},
  editor =	 {G. Watson},
  number =	 {630},
  series =	 {Lecture Notes in Mathemattcs},
  address =	 {New York},
  publisher =	 {Sprmger-Verlag}
}

@inproceedings{JJM88a,
author      = {J. J. Mor\'e},
booktitle   = {Systems Modeling and Optimization},
editor      = {M. Iri and K. Yajima},
publisher   = {Springer-Verlag},
pages       = {1--13},
series      = {Lecture Notes in Control and Information Sciences 113},
title       = {Trust regions and projected gradients},
year        = {1988}
}

@article{JJM94a,
author      = {J. J. Mor\'e},
title       = {Global methods for nonlinear complementarity problems},
journal     = {Math. of Oper. Res.},
pages       = {589--614},
volume      = {21},
year        = {1996},
}

@article{JJM83,
author      = {J. J. Mor\'e and D. C. Sorensen},
journal     = {SIAM J. Sci. Statist. Comput.},
pages       = {553--572},
title       = {Computing a trust region step},
volume      = {4},
year        = {1983}
}

@article{JJM91,
author      = {J. J. Mor\'e and G. Toraldo},
journal     = {SIAM J. Optim.},
pages       = {93--113},
title       = {On the solution of large quadratic programming problems
with bound constraints},
volume      = {1},
year        = {1991}
}


@techreport{MM10a,
  author = "Moreno Marzolla",
  title  = "Optimized Training of Support Vector Machines on the Cell Processor",
  type   = "Technical Report",
  institution = "Department of Computer Science, University of Bologna, Italy",
  number = "UBLCS-2010-02",
  month  = feb,
  year   = 2010,
  url = "http://www.cs.unibo.it/pub/TR/UBLCS/ABSTRACTS/2010.bib?ncstrl.cabernet//BOLOGNA-UBLCS-2010-02"
}

@article{PM15a,
	title={{S}park{N}et: Training Deep Networks in {S}park},
	author={Moritz, Philipp and Nishihara, Robert and Stoica, Ion and Jordan, Michael I},
	journal={arXiv preprint arXiv:1511.06051},
	year={2015}
}

@inproceedings{PM16a,
	title={A linearly-convergent stochastic {L-BFGS} algorithm},
	author={Moritz, Philipp and Nishihara, Robert and Jordan,
		Michael I.},
	booktitle={Proceedings of the Nineteenth International
		Conference on Artificial Intelligence and Statistics},
	year={2016}
}

@article{KGM05a,
        author = "Morse, Jr., Kingsley G.",
        title = "Compression Tools Compared",
        url = "http://www.linuxjournal.com/article/8051",
        journal    = {Linux Journal},
        year = "2005"
}


@book{MoWa64,
author      = {F. Mosteller and D. L. Wallace},
publisher   = {Addison-Wesley},
title       = {Inference and Disputed Authorship: The Federalist Papers},
address     = {Reading, Mass.},
year        = {1964}
}

@inproceedings{JM18a,
    title = "Explainable prediction of medical codes from clinical text",
    author = "Mullenbach, James  and
      Wiegreffe, Sarah  and
      Duke, Jon  and
      Sun, Jimeng  and
      Eisenstein, Jacob",
     booktitle = "Proceedings of the Annual Conference of the North {A}merican Chapter of the Association for Computational Linguistics (NAACL)",
    year = "2018",
    doi = "10.18653/v1/N18-1100",
    pages = "1101--1111"
}

@inproceedings{JM18a-short,
    title = "Explainable Prediction of Medical Codes from Clinical Text",
    author = "Mullenbach, James  and
      Wiegreffe, Sarah  and
      Duke, Jon  and
      Sun, Jimeng  and
      Eisenstein, Jacob",
    booktitle = "NAACL",
    year = "2018"
}


@ARTICLE{KRM95a,
  author     = {Klaus-Robert M{\"u}ller and J. Kohlmorgen and K. Pawelzik},
  title      = {Analysis of Switching Dynamics with Competing Neural Networks},
  journal    = {IEICE Transactions on Fundamentals of Electronics, Communications
                and Computer Sciences},
  volume     = {E78--A},
  number     = {10},
  pages      = {1306--1315},
  year       = {1995},
  keywords   = {controlling chaos},
}

@article{KRM01a,
author      = {K.-R.~{M\"uller} and S. Mika and G.~{R\"atsch} and K. Tsuda
               and B.~{Sch\"ol\-kopf}},
journal     = {IEEE Transactions on Neural Networks},
pages       = {181--201},
title       = {An introduction to kernel-based learning algorithms},
volume      = {12},
number      = {2},
year        = {2001}
}

@InProceedings{KRM97a,
  author	= {K.-R.~{M\"uller} and A.~Smola and G.~{R\"atsch} and
		  B.~{Sch\"ol\-kopf} and J.~Kohlmorgen and V.~Vapnik},
  title		= {Predicting Time Series with Support Vector Machines},
  year		= {1997},
  pages		= {999--1004},
  editor = 	 {W. Gerstner and A. Germond and M. Hasler and J.-D. Nicoud},
  booktitle = 	 "Proceedings of ICANN\'97: : Proc. of the Int. Conf. on
                  Artificial Neural Networks",
  publisher = 	 "Springer",
  address =	 "Berlin"
}

@InProceedings{KRM99a,
  author	= {K.-R.~{M\"uller} and A.~Smola and G.~{R\"atsch} and
		  B.~{Sch\"ol\-kopf} and J.~Kohlmorgen and V.~Vapnik},
  title		= {Predicting Time Series with Support Vector Machines},
  year		= {1999},
  pages		= {243--254},
  editor = 	 {Bernhard Sch\"{o}lkopf and Christopher J. 
		  C. Burges and Alexander J. Smola},
  booktitle = 	 "Advances in Kernel Methods - Support 
		  Vector Learning",
  publisher = 	 "MIT Press",
  address =	 "Cambridge, MA"
}


@inproceedings{MYM08a,
author = {Min Y. Mun and Deborah Estrin and Jeff Burke and Mark Hansen},
title = {Parsimonious Mobility Classification using {GSM} and {W}i{F}i Traces},
booktitle = {Proceedings of the Fifth Workshop on Embedded Networked Sensors (HotEmNets)},
year = {2008}
}


@article{NM80,
author      = {N. Munksgaard},
journal     = {ACM Trans. Math. Software},
pages       = {206--219},
title       = {Solving sparse symmetric sets of linear equations by preconditioned conjugate gradients},
volume      = {6},
year        = {1980}
}


@TechReport{PMM94a,
  author =	 {Murphy, P. M. and Aha, D. W.},
  title =	 {{UCI} Repository of machine
  learning databases},
  year =	 {1994},
  note =         {Data available at {\tt http://www.ics.uci.edu/\verb"~"mlearn/MLRepository.html}},
  institution =  {University of California, Department of Information and Computer 
  Science},
  address = {Irvine, CA}
}

@book{RMS97a,
  editor =       "Roderick Murray-Smith and Tor Arne Johansen",
  title =        "Multiple Model Approaches to Modelling and Control",
  publisher =    "Taylor and Francis, London",
  year =         "1997"
}

@TechReport{BAM95a,
  author = 	 {B. A. Murtagh and Michael Saunders},
  title = 	 {{MINOS} 5.4 User's Guide},
  institution =  {Department of Operations
     Research, Stanford University},
  year = 	 {1995},
  number =	 {SOL 83-20R}
}


@MastersThesis{PM98a,
  author = 	 {Pauli Murto},
  title = 	 {Neural network models for short-term load forecasting},
  school = 	 {Department of Engineering Physics and Mathematics, Helsinki University of Technology},
  year = 	 {1998}
}

@article{SCOP,
  author = {Alexey G. Murzin and Steven E. Brenner and Tim Hubbard and Cyrus
Chothia},
  title = {{SCOP}: A Structural Classification of Protein Database for the
Investigation of Sequences and Structures},
  journal = {Journal of Molecular Biology},
  year = {1995},
  volume = {247},
  pages = {536--540}
}

@misc{CN00a,
    author = "Chikahito Nakajima and M. Pontil and T. Poggio",
    title = "People Recognition and Pose Estimation in Image Sequences",
    year = {2000}
}

@inproceedings{JN14a,
  title={Large-Scale Multi-label Text Classification --- Revisiting Neural Networks},
  author={Nam, Jinseok and Kim, Jungi and Loza Menc{\'\i}a, Eneldo and Gurevych, Iryna and F{\"u}rnkranz, Johannes},
  booktitle="Proceedings of the Joint European Conference on Machine Learning and Knowledge Discovery in Databases (ECML/PKDD)",
  pages={437--452},
  year={2014}
}

@inproceedings{SN16a,
author = {Sharad Nandanwar and M. Narasimha Murty},
title = {Structural Neighborhood Based Classification of Nodes in a Network},
year = {2016},
booktitle = {Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)},
pages = {1085--1094}
}

@article{SN18a, 
title={Overlap-Robust Decision Boundary Learning for Within-Network Classification}, 
journal={Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence (AAAI)},
author={Nandanwar, Sharad and M. Narasimha Murty}, 
year={2018} 
}

@inproceedings{YN19a,
title={Efficient Counterfactual Learning from Bandit Feedback},
author={Narita, Yusuke and Yasui, Shota and Yata, Kohei},
booktitle =	 {Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence (AAAI)},
year={2019}
}

@inproceedings{YN19a-short,
title={Efficient Counterfactual Learning from Bandit Feedback},
author={Narita, Yusuke and Yasui, Shota and Yata, Kohei},
booktitle =	 {AAAI},
year={2019}
}

@techreport{SGN82a,
   title={Truncated-{N}ewton Methods},
   author={Nash, Stephen G.},
   year={1982},
   institution={Department of Computer Science, Stanford University},
  number =	 {STAN-CS-82-906}
}


@techreport{SGN82b,
   title={Preconditioning of truncated-{N}ewton methods},
   author={Nash, Stephen G.},
   year={1982},
   institution={Report 371. Mathematical Sciences Dept., The Johns
Hopkins University}
}
 

@article{SGN85a,
 title={Preconditioning of truncated-{N}ewton methods},
 author={Nash, Stephen G.},
 journal={SIAM Journal on Scientific and Statistical Computing},
 volume={6},
 number={3},
 pages={599--616},
 year={1985},
 publisher={SIAM}
}

@article{SGN85a-short,
 title={Preconditioning of truncated-{N}ewton methods},
 author={Nash, Stephen G},
 journal={SIAM J. Sci. and Stat. Comput.},
 volume={6},
 number={3},
 pages={599--616},
 year={1985}
}

@article{SGN90a,
	title={Assessing a search direction within a truncated-{N}ewton method},
	author={Nash, Stephen G. and Sofer, Ariela},
	journal={Operations Research Letters},
	volume={9},
	number={4},
	pages={219--221},
	year={1990}
}

@article{SGN90a-short,
	title={Assessing a search direction within a truncated-{N}ewton method},
	author={Nash, Stephen G. and Sofer, Ariela},
        journal = 	 {Oper. Res. Lett.},	
	volume={9},
	pages={219--221},
	year={1990}
}

@Book{SGN96a,
  author =	 {Stephen G. Nash and Ariefla Sofer},
  title = 	 {Linear and Nonlinear Programming},
  publisher = 	 {McGraw-Hill},
  year = 	 {1996}
}


@article{SGN00a,
  title={A survey of truncated-{N}ewton methods},
  author={Nash, Stephen G.},
  journal={Journal of Computational and Applied Mathematics},
  volume={124},
  number={1--2},
  pages={45--59},
  year={2000}
}


@article{SGN00a-short,
  title={{A survey of truncated-Newton methods}},
  author={Nash, Stephen G.},
  journal={Journal of CAM},
  volume={124},
  number={1--2},
  pages={45--59},
  year={2000},
  publisher={Elsevier}
}

@inproceedings{NN15a,
  author = {Nagarajan Natarajan and Nikhil Rao and Inderjit S. Dhillon},
  booktitle={International Workshop on Computational Advances in
Multi-Sensor Adaptive Processing (CAMSAP)},
  title={{PU} matrix completion with graph information},
  year={2015},
  pages={37--40}
}

@inproceedings{NN15a-short,
  author = {Nagarajan Natarajan and Nikhil Rao and Inderjit S. Dhillon},
  booktitle={CAMSAP},
  title={{PU} matrix completion with graph information},
  year={2015}
}

@Article{RN98a,
  author = 	 {Ramesh Natarajan},
  title = 	 {An Iterative Scheme for Dense,
Complex-Symmetric, Linear Systems in Acoustics
Boundary-Element Computations},
  journal = 	 {SIAM J. Sci. Comput.},
  year = 	 {1998},
  volume =	 {19},
  number =	 {5},
  pages =	 {1450--1470}
}



@Article{KSN95a,
  author = 	 {Kumpati S. Narendra and Jeyendran Balakrishnan and M. Kemal Ciliz},
  title = 	 {Adaptation and learning using multiple models, switching, and tuning},
  journal = 	 {IEEE  Control System Magazine},
  year = 	 {1995},
  volume =	 {15},
  number =	 {3},
  pages =	 {37--51}
}

@inproceedings{SN12a,
 author = {Nath, Suman},
 title = {{ACE}: exploiting correlation for energy-efficient and continuous context sensing},
 booktitle = {Proceedings of the 10th International Conference on Mobile Systems, Applications, and Services (MobiSys)},
 year = {2012},
 pages = {29--42}
}


@misc{IN13a,
author={Necoara, Ion and Clipici, Dragos},
title={Distributed coordinate descent methods for composite minimization},
note={arXiv preprint arXiv:1312.5302},
year={2013}
}

@article{IN13b,
author = {Necoara, Ion and Patrascu, Andrei},
year = {2013},
pages="307--337",
title = {A random coordinate descent algorithm for optimization problems with
composite objective function and linear coupled constraints},
volume = {57},
journal = {Computational Optimization and Applications}
}

@article{IN13b-short,
author = {Necoara, Ion and Patrascu, Andrei},
year = {2013},
pages="307--337",
title = {A random coordinate descent algorithm for optimization problems with
composite objective function and linear coupled constraints},
volume = {57},
journal = {Comput. Opt. App.}
}

@ARTICLE{IN13c, 
author={Ion Necoara}, 
journal={IEEE Transactions on Automatic Control}, 
title={Random Coordinate Descent Algorithms for Multi-Agent Convex Optimization Over Networks}, 
year={2013}, 
volume={58}, 
number={8}, 
pages={2001--2012}
}

@article{AN01a,
  author = {Angelia Nedi\'c and Dimitri P. Bertsekas and Vivek S. Borkar},
  title = {Distributed asynchronous incremental subgradient methods},
  journal = {Studies in Computational Mathematics},
  volume = {8},
  pages = {381--407},
  year = {2001}
}

@article{JAN65a,
  title={A simplex method for function minimization},
  author={Nelder, John A. and Mead, Roger},
  journal={The Computer Journal},
  volume={7},
  number={4},
  pages={308--313},
  year={1965}
}

@article{YEN83a,
	title={A method of solving a convex programming problem with convergence rate $O (1/k^2)$},
	author={Nesterov, Yurii E.},
	journal={Soviet Mathematics Doklady},
	volume={27},
	pages={372--376},
	year={1983}
}


@TechReport{YEN89a,
  author = 	 {Yurii Nesterov and A. Nemirovskii},
  title = 	 {Self-concordant functions and polynomial time
methods in convex programming},
  institution =  {Central Economic \& Mathematical Institute, USSR Acad.
Sci.},
  year = 	 {1989},
  type =	 {Preprint},
  address =	 {Moscow, USSR}
}


@Book{YEN94a,
  author = 	 {Yurii E. Nesterov and A. Nemirovskii},
  title = 	 {Interior Point Polynomial Methods in Convex
                  Programming: Theory and Applications},
  publisher = 	 {Society for Industrial and Applied Mathematics},
  year = 	 {1994},
  address =	 {Philadelphia}
}




@TechReport{YEN95a,
  author = 	 {Yurii E. Nesterov and M. J. Todd},
  title = 	 {Primal-Dual Interior-Point Methods for Self-Scaled Cones},
  institution =  {school of Operations Research and Industrial
                  Engineering, Cornell University},
  year = 	 {1995},
  number =	 {1125},
  note =         {To appear in {\em SIAM J. Optim.}}
}
% checked April 23

@Book{YEN03a,
  author =       {Yurii E. Nesterov},
  title =        {Introductory Lectures on Convex Optimization: A Basic Course},
  publisher =    {Kluwer Academic Publishers},
  year =         {2003},
}

@article{YEN09a,
 title = {Primal-dual Subgradient Methods for Convex Problems},
 author = {Nesterov, Yurii E.},
 journal = {Mathematical Programming},
 volume = {120},
 number = {1},
 pages = {221--259},
 year = {2009}
}

@Article{YEN10a,
title={Efficiency of coordinate descent methods on huge-scale optimization problems},
author={Yurii E. Nesterov},
journal={SIAM Journal on Optimization},
volume={22},
number={2},
pages={341--362},
year={2012}
}


@Article{YEN10a-short,
title={Efficiency of coordinate descent methods on huge-scale optimization problems},
author={Yurii E. Nesterov},
journal = 	 {SIAM J. Optim.},
volume={22},
number={2},
pages={341--362},
year={2012}
}

@article{YEN13a,
	title={Gradient methods for minimizing composite functions},
	author={Nesterov, Yurii E.},
	journal={Mathematical Programming},
	volume={140},
	number={1},
	pages={125--161},
	year={2013},
	publisher={Springer}
}

@inproceedings{YN11a,
  title={Reading Digits in Natural Images with Unsupervised Feature Learning},
  author={Netzer, Yuval and Wang, Tao and Coates, Adam and Bissacco, Alessandro and Wu, Bo and Ng, Andrew Y.},
  Booktitle = {NIPS Workshop on Deep Learning and Unsupervised Feature Learning},
  Year = {2011}
}

@techreport{AN97,
author      = "Arnold Neumaier",
title       = "On satisfying second-order optimality conditions
               using modified Cholesky factorizations",
type        = "{T}echnical {R}eport",
institution = "Universitat Wien",
address     = "Vienna, Austria",
year        = "1997",
}

@article{DM09a,
  title={Distributed algorithms for topic models},
  author={Newman, David and Asuncion, Arthur and Smyth, Padhraic and Welling, Max},
  journal={Journal of Machine Learning Research},
  volume={10},
  pages={1801--1828},
  year={2009}
}


@inproceedings{BN15a,
 Author={Behnam Neyshabur and Nathan Srebro},
 title={On Symmetric and Asymmetric {LSH}s for Inner Product
Search},
 year={2015},
 Booktitle={Proceedings of the Thirty-Second International Conference on
Machine Learning (ICML)},
 pages={1926--1934},
}

@inproceedings{BN15a-short,
 Author={Behnam Neyshabur and Nathan Srebro},
 title={On Symmetric and Asymmetric {LSH}s for Inner Product
Search},
 year={2015},
 Booktitle={ICML},
 pages={1926--1934},
}


@incollection{BN15b,
title = {Path-{SGD}: Path-Normalized Optimization in Deep Neural Networks},
author = {Neyshabur, Behnam and Salakhutdinov, Ruslan R. and Srebro, Nati},
booktitle = {Advances in Neural Information Processing Systems 28},
editor = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
pages = {2422--2430},
year = {2015}
}


@inproceedings{AYN01a,
    title = {On Spectral Clustering: Analysis and an algorithm},
    author = {Andrew Y. Ng and Michael I. Jordan and Yair Weiss},
    booktitle = {Proceedings of NIPS},
    pages = {849--856},
    year = {2001},
}

@inproceedings{AYN04a,
        title = {Feature selection, {L}1 vs. {L}2 regularization, and rotational invariance},
        author = {Andrew Y. Ng},
        booktitle = {Proceedings of the Twenty First International Conference on Machine Learning (ICML)},
        year = {2004}
}

@inproceedings{TN24a,
   title = "Noise Contrastive Estimation-based Matching Framework for Low-resource Security Attack Pattern Recognition",
   author = "Nguyen, Tu and {\v{S}}rndi\'{c}, Nedim and Neth, Alexander",
   booktitle = "Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics",
   year = "2024",
}

@inproceedings{AN05a, 
  author = {Niculescu-Mizil, Alexandru and Caruana, Rich},
  title = {Predicting Good Probabilities with Supervised Learning},
  year = {2005},
  booktitle = {Proceedings of the 22nd International Conference on Machine Learning (ICML)},
  pages = {625--632}
}

@article{KN00a,
    author = "Kamal Nigam and Andrew K. McCallum and Sebastian Thrun and
Tom M. Mitchell",
    title = "Text Classification from Labeled and Unlabeled Documents
using {EM}",
    journal = "Machine Learning",
    volume = "39",
    number = "2/3",
    pages = "103--134",
    year = "2000",
    url = "citeseer.ist.psu.edu/article/nigam99text.html" 
}


@ONLINE{NIKE12a,
	author = {Nike},
	title = {Fuelband},
        howpublished = {\url{http://www.nike.com/us/en_us/c/nikeplus-fuelband}}	
}


@ONLINE{NIKE08a,
	author = {Nike},
	title = {Nike+ Sport Kit},
        howpublished = {\url{http://nikeplus.nike.com/plus/}}	
}

@inproceedings{XN11a,
    title={{SLIM}: Sparse linear methods for top-n recommender systems},
    author={Ning, Xia and Karypis, George},
 booktitle = {Proceedings of the 11th International Conference on Data Mining},
    pages={497--506},
    year={2011}
}

@inproceedings{XN11a-short,
    title={{SLIM}: Sparse linear methods for top-n recommender systems},
    author={Ning, Xia and Karypis, George},
 booktitle = {ICDM},
    year={2011}
}

@inproceedings{FN11a,
  author    = {Feng Niu and Benjamin Recht and Christopher R\'e and Stephen J. Wright},
 title ={{HOGWILD}!: a lock-free approach to parallelizing stochastic gradient descent},
 booktitle = {Advances in Neural Information Processing Systems 24},
 editor = {J. Shawe-Taylor and R.S. Zemel and P. Bartlett and F.C.N. Pereira and K.Q. Weinberger},
 pages = {693--701},
 year = {2011}
}

@inproceedings{FN11a-short,
  author    = {Feng Niu and Benjamin Recht and Christopher R\'e and Stephen J. Wright},
 title ={{HOGWILD}!: a lock-free approach to parallelizing stochastic gradient descent},
 booktitle = {NIPS},
 year = {2011}
}

@inproceedings{YN12a,
 author={Yanzhi Niu and Yi Wang and Gordon Sun and Aden Yue and Brian Dalessandro and Claudia Perlich and Ben Hamner},
 title={The {T}encent Dataset and {KDD}-{C}up'12},
 booktitle={ACM SIGKDD KDD-Cup WorkShop},
 year={2012}
}

@inproceedings{JN03a,
author = {Nivre, Joakim},
booktitle = {Proceedings of the 8th International Workshop on Parsing
Technologies (IWPT 03)},
title = {An Efficient Algorithm for Projective Dependency Parsing},
year = {2003}
}

@inproceedings{JN05a,
author = {Nivre, Joakim and Hall, Johan},
booktitle = {Proceedings of the Fourth Workshop on Treebanks and
Linguistic Theories},
title = {Malt{P}arser: A Language-Independent System for Data-Driven
Dependency Parsing},
year = {2005}
}

@inproceedings{JN06a,
author = {Nivre, Joakim and Hall, Johan and Nilsson, Jens and   
Eryi\v{g}it, G\"ul\c{s}en and Marinov, Svetoslav},
booktitle = {Proceedings of the Tenth Conference on Computational  
Natural Language Learning (CoNLL)},
title = {Labeled pseudo-projective dependency parsing with Support  
Vector Machines},
pages = {221--225},
year = {2006}
}

@article{JN07a,
author = {Nivre, Joakim and Hall, Johan and Nilsson, Jens and Chanev, Atanas
and Eryigit, Gulsen and Kubler, Sandra and Marinov, Svetoslav and  
Marsi, Erwin},
title = {Malt{P}arser: A Language-Independent System for Data-Driven
Dependency Parsing},
year = {2007},
journal = {Natural Language Engineering},
volume = {13},
number={2},
pages={95--135}
}

@article{JN91a,
  title={A Numerical Study of the Limited Memory {BFGS} Method and the Truncated-Newton Method for Large Scale Optimization},
  author={Nocedal, Jorge and Nash, Stephen G.},
  journal={SIAM Journal on Optimization},
  volume={1},
  number={3},
  year={1991},
  pages={358--372}
}

@book{JN99a,
author="Jorge Nocedal and Stephen J. Wright",
title = "Numerical Optimization",
year = "1999",
  publisher = 	 {Springer-Verlag},
  address =      {New York, NY}
}

@book{JN99a-short,
author="Jorge Nocedal and Stephen J. Wright",
title = "Numerical Optimization",
year = "1999"
}

@book{JN06b,
	title={Numerical Optimization},
	author={Nocedal, Jorge and Wright, Stephen},
        edition = {second},
	year={2006},
	publisher={Springer}
}

@Misc{NN01a,
  title =	 {{N}eural {N}etwork {FAQ}},
  note={Periodic posting to the Usenet newsgroup comp.ai.neural-nets},
  url =	 {ftp://ftp.sas.com/pub/neural/FAQ.html},
  author={Warren S. Sarle},
  year={1997}
}

@article{CN68,
author     = {C.E. Nugent and T.E. Vollman and J. Ruml},
journal    = {Oper. Res.},
pages      = {150--173},
title      = {An experimental comparison of techniques for the assignment 
	      of facilities to locations},
volume     = {16},
year       = {1968}
}

@misc{SN19a,
      title={Natural language processing of {MIMIC-III} clinical notes for identifying diagnosis and procedures with neural networks}, 
      author={Siddhartha Nuthakki and Sunil Neela and Judy W. Gichoya and Saptarshi Purkayastha},
      year={2019},
      eprint={1912.12397},
      archivePrefix={arXiv}
}

@inproceedings{DO98a,
  title={Implicit feedback for recommender systems},
  author={Oard, Douglas W. and Kim, Jinmook},
  booktitle={Proceedings of the AAAI workshop on recommender systems},
  pages = {81--83},
  year={1998}
}

@inproceedings{DO98a-short,
  title={Implicit feedback for recommender systems},
  author={Oard, Douglas W. and Kim, Jinmook},
  booktitle={AAAI workshop on recommender systems},
  year={1998}
}

@misc{MO04a,
title={The {S}cala language specification},
author={Odersky, Martin and Altherr, Philippe and Cremet, Vincent and Emir, Burak and Micheloud, Stphane and Mihaylov, Nikolay and Schinz, Michel 
and Stenman, Erik and Zenger, Matthias},
year={2004}
}

@book{MO08a,
        title={Programming in {S}cala},
        author={Odersky, Martin and Spoon, Lex and Venners, Bill},
        year={2008},
        publisher={Artima}
}

@inproceedings{CO08a,
 author = {Olston, Christopher and Reed, Benjamin and Srivastava, Utkarsh and Kumar, Ravi and Tomkins, Andrew},
 title = {Pig latin: a not-so-foreign language for data processing},
 booktitle = {Proceedings of the 2008 ACM SIGMOD international conference on Management of data},
 year = {2008},
 pages = {1099--1110}
} 

@misc{JO21a,
      title={{Macro F1 and Macro F1}}, 
      author={Juri Opitz and Sebastian Burst},
      year={2021},
      eprint={1911.03347},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      note={arXiv preprint arXiv:1911.03347}      
}

@InProceedings{MO00a,
  author = 	 {M. Opper and O. Winther},
  editor = 	 {A. Smola and P. Bartlett and B. Sch\"olkopf and D.
Schuurmans},
  title = 	 {Gaussian Processes and {SVM}: Mean Field and Leave-One-Out
Estimator},
  booktitle = 	 {Advances in Large Margin Classifiers},
  year = 	 {2000},
  publisher = 	 {MIT Press},
  address = 	 {Cambridge, MA}
}



@book{JMO88,
author      = {J. M. Ortega},
publisher   = {Plenum Press},
title       = {Introduction to Parallel and Vector Solution of Linear Systems},
year        = {1988},
address     = {New York}
}

		  

@TechReport{MO96a,
  author =   {M.J.L. Orr},
  title =    {Introduction to radial basis function networks},
  institution =  {Institute for Adaptive and Neural Computation, Edinburgh University},
  year =     {1996},
  note = {{\tt http://www.anc.ed.ac.uk/\verb"#"mjo/rbf.html}}
}

@InProceedings{KO19a,
  author    = {Kazuki Osawa and
               Yohei Tsuji and
               Yuichiro Ueno and
               Akira Naruse and
               Rio Yokota and
               Satoshi Matsuoka},
  title={Large-Scale Distributed Second-Order Optimization Using Kronecker-Factored Approximate Curvature for Deep Convolutional Neural Networks},
   booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year			= {2019}
}

@Article{MRO00a,
  author = {Michael R. Osborne and Brett Presnell
and Berwin A. Turlach},
  title = {A New Approach to Variable Selection in
   Least Squares Problems},
  journal = {IMA Journal of Numerical Analysis},
  year = {2000},
  pages = {389--404},
  volume = {20}
}
  
@Article{MRO00b,
  author =       {Michael R. Osborne and Brett Presnell and Berwin A. Turlach},
  title =        {On the {LASSO} and its dual},
  journal =      {Journal of Computational and Graphical Statistics},
  volume =      {9},
  number =      {2},
  pages =        {319--337},
  year =         {2000}
}
  
@InProceedings{EO97a,
  author = 	 "Osuna, E. and Freund, R. and Girosi, F.",
  title = 	 "Training Support Vector Machines: An Application to
   Face Detection",
  booktitle =	 "Proceedings of 
IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR)",
  year =	 "1997",
  pages={130--136}
}
%  publisher={IEEE},
%  address={New York, NY}

@InProceedings{EO97a-short,
  author =   "Osuna, E. and Freund, R. and Girosi, F.",
  title =    "Training Support Vector Machines: An Application to
   Face Detection",
  booktitle =    "CVPR",
  year =     "1997"
}

@TechReport{EO97b,
  author = 	 "Osuna, E. and Freund, R. and Girosi, F.",
  title = 	 "Support Vector Machines: Training
     and Applications",
  institution =  "Massachusetts Institute of Technology",
  year = 	 "1997",
  type =	 "AI Memo",
  number =	 "1602"
}

		  
		  
@InProceedings{EO97c,
  author = 	 "Osuna, E. and Freund, R. and Girosi, F.",		  
  title = 	 "An improved training algorithm for support vector machines",
  booktitle =	 "Proceedings of IEEE NNSP'97",
  year =	 "1997"
}

@InProceedings{EO98a,
  author = "E. Osuna and F. Girosi",
  title = "Reducing the run-time complexity of support vector machines",
  booktitle = "Proceedings of International Conference on Pattern Recognition",
  year = "1998",
  url = "citeseer.nj.nec.com/osuna98reducing.html" 
}

@inproceedings{WP10a,
  title={Transfer learning in collaborative filtering for sparsity reduction},
  author={Pan, Weike and Xiang, Evan Wei and Liu, Nathan Nan and Yang, Qiang},
  booktitle={Proceedings of the Twenty-fourth AAAI conference on artificial intelligence},
  pages = {230--235},  
  year={2010}
}

@inproceedings{WP10a-short,
  title={Transfer learning in collaborative filtering for sparsity reduction},
  author={Pan, Weike and Xiang, Evan Wei and Liu, Nathan Nan and Yang, Qiang},
  booktitle={AAAI},
  year={2010}
}

@inproceedings{WP11a,
author = {Pan, Weike and Liu, Nathan N. and Xiang, Evan W. and Yang, Qiang},
 title = {Transfer Learning to Predict Missing Ratings via Heterogeneous User Feedbacks},
 booktitle = {Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence (IJCAI)},
 year = {2011},
 pages = {2318--2323}
}

@inproceedings{WP11a-short,
author = {Pan, Weike and Liu, Nathan N. and Xiang, Evan W. and Yang, Qiang},
 title = {Transfer Learning to Predict Missing Ratings via Heterogeneous User Feedbacks},
 booktitle = {IJCAI},
 year = {2011}
}

@inproceedings{WP13a,
  title={{GBPR}: Group preference based {B}ayesian personalized ranking for one-class collaborative filtering},
  author={Pan, Weike and Chen, Li},
  booktitle={Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence (IJCAI)},
  pages={2691--2697},
  year={2013}
}

@Article{PP94a,
  author = 	 {Pentti Paatero and Unto Tapper},
  title = 	 {Positive matrix factorization: A non-negative factor model with optimal utilization of error},
  journal = 	 {Environmetrics},
  year = 	 {1994},
  OPTkey = 	 {},
  volume =	 {5},
  OPTnumber = 	 {},
  pages =	 {111--126},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}


@Article{PP99a,
  author =       "Pentti Paatero",
  title =        "The Multilinear Engine---{A} Table-Driven, Least
                 Squares Program for Solving Multilinear Problems,
                 Including the $n$-Way Parallel Factor Analysis Model",
  journal =      {Journal of Computational and Graphical Statistics},
  volume =       "8",
  number =       "4",
  pages =        "854--888",
  year =         "1999"
}


@Book{MWP96,
  author = 	 {M. W. Padberg and M. P. Rijal},
  title = 	 {Location, Scheduling and Integer Programming},
  publisher = 	 {Kluwer Academic Press},
  year = 	 {1996},
  address =	 {Norwell MA}
}


@inproceedings{JP10a,
author = {Paek, Jeongyeup and Kim, Joongheon and Govindan, Ramesh},
title = {Energy-efficient rate-adaptive {GPS}-based positioning for smartphones},
booktitle = {Proceedings of the 8th international conference on Mobile systems, applications, and services},
series = {MobiSys '10},
year = {2010},
isbn = {978-1-60558-985-5},
location = {San Francisco, California, USA},
pages = {299--314},
numpages = {16},
url = {http://doi.acm.org/10.1145/1814433.1814463},
doi = {10.1145/1814433.1814463},
acmid = {1814463},
publisher = {ACM},
address = {New York, NY, USA},
keywords = {GPS, adaptive positioning, energy-efficient, sensor, smartphone},
}

@Article{LP02a,
  author =       {Laura Palagi and Marco Sciandrone},
  title =        {On the convergence of a modified version of {SVM}$^{light}$ Algorithm},
  journal={Optimization Methods and Software},
  volume={20},
  pages={315--332},
number={2--3},
year={2005}
}

@Article{LP02a-short,
  author =       {Laura Palagi and Marco Sciandrone},
  title =        {On the convergence of a modified version of {SVM}$^{light}$ Algorithm},
  journal = {Optim. Methods Softw.},  
  volume={20},
  pages={315--332},
year={2005}
}

@inproceedings{RP08a,
  title={One-class collaborative filtering},
  author={Pan, Rong and Zhou, Yunhong and Cao, Bin and Liu, Nathan N and Lukose, Rajan and Scholz, Martin and Yang, Qiang},
  booktitle={IEEE International Conference on Data Mining (ICDM)},
  pages={502--511},
  year={2008}
}

@inproceedings{RP08a-short,
  title={One-class collaborative filtering},
  author={Pan, Rong and Zhou, Yunhong and Cao, Bin and Liu, Nathan N and Lukose, Rajan and Scholz, Martin and Yang, Qiang},
  booktitle={ICDM},
  year={2008}
}


@inproceedings{RP09a,
 author = {Pan, Rong and Scholz, Martin},
 title = {Mind the Gaps: Weighting the Unknown in Large-scale One-class Collaborative Filtering},
 booktitle = {Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)},
 year = {2009},
 pages = {667--676}
} 

@inproceedings{RP09a-short,
 author = {Pan, Rong and Scholz, Martin},
 title = {Mind the Gaps: Weighting the Unknown in Large-scale One-class Collaborative Filtering},
 booktitle = {KDD},
 year = {2009}
} 

@article{BP09a,
  title={{PLANET}: massively parallel learning of tree ensembles with MapReduce},
  author={Biswanath Panda and Joshua S. Herbach and Sugato Basu and Roberto J. Bayardo},
  journal={Proceedings of VLDB},
  volume={2},
  number={2},
  pages={1426--1437},
  year={2009}
}

@inproceedings{BP05a,
title = "Seeing Stars: Exploiting Class Relationships for Sentiment Categorization with Respect to Rating Scales",
author = "Pang, Bo  and
Lee, Lillian",
editor = "Knight, Kevin  and
Ng, Hwee Tou  and
Oflazer, Kemal",
booktitle = "Proceedings of the Forty-Third Annual Meeting of the Association for Computational Linguistics (ACL)",
year = "2005",
doi = "10.3115/1219840.1219855",
pages = "115--124",
}

@article{JSP87a,
title={A posteriori error bounds for the linearly-constrained variational inequality problem},
author={Pang, Jong-Shi},
journal={Mathematics of Operations Research},
volume={12},
number={3},
pages={474--484},
year={1987}
}

@article{JSP93a,
	author      = {Jong-Shi Pang and Liqun Qi},
	journal     = {SIAM Journal on Optimization},
	title       = {Nonsmooth Equations: Motivation and Algorithms},
	volume      = {3},
	pages       = {443--465},
	year        = {1993}
}

@inproceedings{JP18a,
title={Field-weighted Factorization Machines for Click-Through Rate Prediction in Display Advertising},
author={Pan, Junwei and Xu, Jian and Ruiz, Alfonso Lobos and Zhao, Wenliang and Pan, Shengjun and Sun, Yu and Lu, Quan},
booktitle={Proceedings of the International Conference on World Wide Web},
pages={1349--1357},
year={2018}
}

@InProceedings{CP98a,
  author	= {C.~Papageorgiou and M.~Oren and T.~Poggio},
  title		= {A General Framework for Object Detection},
  booktitle	= {International Conference on Computer Vision {ICCV}'98},
  year		= {1998},
  url		= {http://www.ai.mit.edu/people/cpapa/publications/gen-obj-det-iccv98.ps.gz}
		  
}

@inproceedings{UP13a,
  title={One-class collaborative filtering with random graphs},
  author={Paquet, Ulrich and Koenigstein, Noam},
  booktitle={Proceedings of the 22nd International Conference on World Wide Web},
  pages={999--1008},
  year={2013}
}

@inproceedings{UP13a-short,
  title={One-class collaborative filtering with random graphs},
  author={Paquet, Ulrich and Koenigstein, Noam},
  booktitle={WWW},
  year={2013}
}

@inproceedings{PP14a,
 author = {Parambath, Shameem A. Puthiya and Usunier, Nicolas and Grandvalet, Yves},
 booktitle = {Advances in Neural Information Processing Systems},
 title = {Optimizing {F}-measures by cost-sensitive classification},
 volume = {27},
 year = {2014}
}

@Book{PMP94a,
editor = {P. M. Pardalos and H. Wolkowicz}, 
series = {{DIMACS} Series on Discrete Mathematics and
Theoretical
Computer Science},
publisher = {American Mathematical Society},
volume = {16},
pages = {237--261},
year = {1994},
title = {Quadratic Assignment and Related Problems} 
}



@InCollection{PMP94b,
  author = 	 {P. M. Pardalos and F. Rendl and H. Wolkowicz},
  title = 	 {The quadratic assignment problem : a survey and 
                  recent development},
        booktitle = {Quadratic assignment and related problems}, 
        editor = {P.M. Pardalos and H. Wolkowicz}, 
        series = {{DIMACS} Series on Discrete Mathematics and
Theoretical
                  Computer Science},
        publisher = {American Mathematical Society},
        volume = {16},
        pages = {237--261},
        year = {1994}
}

@inproceedings{HP22a,
  author    = {Park, Hyunji and
               Vyas, Yogarshi and
               Shah, Kashif},
  title     = {Efficient Classification of Long Documents Using Transformers},
  booktitle = {Proceedings of the Annual Meeting of the Association for Computational Linguistics},
  pages     = {702--709},
  year      = {2022},
  doi       = {10.18653/v1/2022.acl-short.79}
}

@inproceedings{HP22a-short,
  author    = {Park, Hyunji and
               Vyas, Yogarshi and
               Shah, Kashif},
  title     = {Efficient Classification of Long Documents Using Transformers},
  booktitle = {ACL},
  year      = {2022},
}


@article{JP07a,
  title={{SVDD}-based Pattern Denoising},
  author={Park, Jooyoung and Kang, Daesung and Kim, Jongho and Kwok, James T. and Tsang, Ivor W.},
  journal={Neural Computation},
  volume={19},
  number={7},
  pages={1919--1938},
  year={2007},
  publisher={MIT Press}
}



@Article{MYP07a,
  author = {Mee Young Park and Trevor Hastie},
  title = {L1 Regularization Path Algorithm for Generalized Linear Models},
  journal = {Journal of the Royal Statistical Society Series B},
  year = {2007},
  pages = {659--677},
  volume = {69}
}

@inproceedings{STP09a,
  title = {Pairwise preference regression for cold-start recommendation},
  author = {Park, Seung-Taek and Chu, Wei},
  booktitle = {Proceedings of the third ACM conference on Recommender systems},
  pages = {21--28},
  year = {2009}
}

@inproceedings{STP09a-short,
  title = {Pairwise preference regression for cold-start recommendation},
  author = {Park, Seung-Taek and Chu, Wei},
  booktitle = {RecSys},
  year = {2009}
}

@article{IP15a,
  title={{LSHTC}: A benchmark for large-scale text classification},
  author={Partalas, Ioannis and Kosmopoulos, Aris and Baskiotis, Nicolas and Artieres, Thierry and Paliouras, George and Gaussier, Eric and Androutsopoulos, Ion and Amini, Massih-Reza and Galinari, Patrick},
  journal={arXiv preprint arXiv:1503.08581},
  year={2015}
}

@inproceedings{FP13a,
  title={Sensorlose Zustands{\"u}berwachung an Synchronmotoren},
  author={Paschke, Fabian and Bayer, Christian and Bator, Martyna and M{\"o}nks, Uwe and Dicks, Alexander and Enge-Rosenblatt, Olaf and Lohweg, Volker},
  booktitle={Proceedings of Computational Intelligence Workshop},
  year={2013}
}

@article{AP17a,
  title={Automatic differentiation in {P}ytorch},
  author={Paszke, Adam and Gross, Sam and Chintala, Soumith and Chanan, Gregory and Yang, Edward and DeVito, Zachary and Lin, Zeming and Desmaison, Alban and Antiga, Luca and Lerer, Adam},
  year={2017}
}

@incollection{AP19a,
title = {Py{T}orch: An Imperative Style, High-Performance Deep Learning  Library},
author = {Paszke, Adam and Gross, Sam and Massa, Francisco and Lerer,  Adam and Bradbury, James and Chanan, Gregory and Killeen, Trevor and  Lin, Zeming and Gimelshein, Natalia and Antiga, Luca and Desmaison,  Alban and Kopf, Andreas and Yang, Edward and DeVito, Zachary and  Raison, Martin and Tejani, Alykhan and Chilamkurthy, Sasank and  Steiner, Benoit and Fang, Lu and Bai, Junjie and Chintala, Soumith},
booktitle = {Advances in Neural Information Processing Systems 32},
editor = {H. Wallach and H. Larochelle and A. Beygelzimer and F.  d\textquotesingle Alch\'{e}-Buc and E. Fox and R. Garnett},
pages = {8024--8035},
year = {2019}
}

@TechReport{GP94a,
  author = 	 {G. Pataki},
  title = 	 {On the facial structure of cone-LP's
and semidefinite programs},
  institution =  {Graduate School of Industrial Administration,
Carnegie Mellon University},
  year = 	 {1994},
  type =	 {Management Science Research Report},
  number =	 {MSRR-595}
}

@article{AP07a,
        author    = {A. Paterek},
        title     = {Improving Regularized {S}ingular {V}alue {D}ecomposition for collaborative filtering},
        journal   = {Proceedings of KDD Cup and Workshop},
        year      = {2007},
}

@Article{AP15a,
author="Patrascu, Andrei and Necoara, Ion",
title="Efficient random coordinate descent algorithms for large-scale structured nonconvex optimization",
journal="Journal of Global Optimization",
year="2015",
volume="61",
number="1",
pages="19--46"
}

@inproceedings{DP00a,
    author = "Dmitry Pavlov and Darya Chudova and Padhraic Smyth",
    title = "Towards scalable support vector machines using squashing",
    booktitle = "Proceedings of ACM Conference on Knowledge Discovery and Data Mining",
    pages = "295--299",
    year = "2000",
    url = "http://citeseer.nj.nec.com/article/pavlov00towards.html"
}


  @InProceedings{KP94a,
author = "K. Pawelzik",
  title = "Detecting coherence in neuronal data",
  booktitle = 	 {Physics of neural networks},
  year =	 {1994},
  editor =	 {Van Hemmen, L. and Schulten, K.},
  publisher =	 {Springer}
}



@article{KP96a,
    author = "Klaus Pawelzik and Jens Kohlmorgen and
Klaus-Robert M{\"u}ller",
    title = "Annealed Competition of Experts for
a Segmentation and Classification of Switching Dynamics",
    journal = "Neural Computation",
    volume = "8",
    number = "2",
    pages = "340--356",
    year = "1996",
    url = "http://citeseer.nj.nec.com/pawelzik96annealed.html"
}


@article{BAP94a,
  title={Fast exact multiplication by the {H}essian},
  author={Pearlmutter, Barak A.},
  journal={Neural Computation},
  volume={6},
  number={1},
  pages={147--160},
  year={1994}
}

@InCollection{DP11a,
  author = 	 {Dmitry Pechyony and Libin Shen and Rosie Jones},
  title = 	 {Solving Large Scale Linear SVM with Distributed Block Minimization},
  booktitle = 	 {NIPS 2011 Workshop on Big Learning: Algorithms, Systems, and Tools for Learning at Scale},
  OPTcrossref =  {},
  OPTkey = 	 {},
  OPTpages = 	 {},
  OPTpublisher = {},
  year =	 {2011},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTtype = 	 {},
  OPTchapter = 	 {},
  OPTaddress = 	 {},
  OPTedition = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@article{FP11a,
title={Scikit-learn: machine learning in {P}ython},
 author = {Pedregosa, Fabian and Varoquaux, Ga\"{e}l and Gramfort, Alexandre and Michel, Vincent and Thirion, Bertrand and Grisel, Olivier and Blondel, Mathieu and Prettenhofer, Peter and Weiss, Ron and Dubourg, Vincent and Vanderplas, Jake and Passos, Alexandre and Cournapeau, David and Brucher, Matthieu and Perrot, Matthieu and Duchesnay, \'{E}douard},
journal={Journal of Machine Learning Research},
volume={12},
pages={2825--2830},
year={2011}
}


@article{FP11a-short,
title={Scikit-learn: machine learning in {P}ython},
 author = {Pedregosa, Fabian and Varoquaux, Ga\"{e}l and Gramfort, Alexandre and Michel, Vincent and Thirion, Bertrand and Grisel, Olivier and Blondel, Mathieu and Prettenhofer, Peter and Weiss, Ron and Dubourg, Vincent and Vanderplas, Jake and Passos, Alexandre and Cournapeau, David and Brucher, Matthieu and Perrot, Matthieu and Duchesnay, \'{E}douard},
journal={JMLR},
volume={12},
pages={2825--2830},
year={2011}
}


@incollection {RNP60a,
  booktitle = "Contributions to Probability and Statistics",
  author =	 {Robert N. Pendergrass and Ralph A. Bradley},
  editor      = {O. Olkin and S. G. Ghurye and W. Hoeffding
                and W. G. Madow and H. B. Mann},
  title = 	 {Ranking in triple comparisons},
  year = 	 {1960},
  pages       = {331--351},
  publisher = 	 "Stanford University Press",
  address =	 "Stanford, CA",
  OPTkey = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTtype = 	 {},
  OPTaddress = 	 {},
  OPTedition = 	 {},
  OPTmonth = 	 {},
  OPTpages = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@InProceedings{FP04a,
  author = {Fuchun Peng and Fangfang Feng and Andrew McCalum},
  title = {Chinese segmentation and new word detection using
conditional random fields},
  booktitle = {Proceedings of The 20th International Conference on
Computational Linguistics~(COLING)},
  year = {2004},
  pages = {562--568}
}

@inproceedings{JP14a,
  author = {Jeffrey Pennington and Richard Socher and Christopher D. Manning},
  booktitle = {Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP)},
  title = {GloVe: Global Vectors for Word Representation},
  year = {2014},
  pages = {1532--1543},
  url = {http://www.aclweb.org/anthology/D14-1162}
}

@inproceedings{JP14a-short,
  author = {Jeffrey Pennington and Richard Socher and Christopher D. Manning},
  booktitle = {EMNLP},
  title = {GloVe: Global Vectors for Word Representation},
  year = {2014}
}

@InProceedings{FPC03a,
  author =	 {Perez Cruz, F. and  J. Weston and  D. J. L. Herrmann and B.
Sch\"{o}lkopf},
  editor =	 {J. Suykens and G. Horvath and S. Basu and C. Micchelli and J. Vandewalle},
  title = 	 {Extension of the $\nu$-SVM range for classification},
  publisher = 	 {IOS Press},
  year = 	 {2003},
  series ={190},
  address =	 {Amsterdam},
  booktitle = 	 {Advances
in Learning Theory: Methods, Models and Applications},
  pages =	 {179--196}
}

@INPROCEEDINGS{FP04b,
  author = {Fernando P\'erez-Cruz and An\'ibal R. Figueiras-Vidal and Antonio Art\'es-Rodr\'iguez},
  title = {Double chunking for solving {SVM}s for very large datasets},
  booktitle = {Proceedings of Learning 2004, Spain},
  year = {2004}
}


@article{SP03a,
  author    = {Simon Perkins and
               Kevin Lacker and
               James Theiler},
  title     = {Grafting: Fast, Incremental Feature Selection by Gradient
               Descent in Function Space},
  journal   = {Journal of Machine Learning Research},
  volume    = {3},
  year      = {2003},
  pages     = {1333--1356},
  ee        = {http://www.jmlr.org/papers/v3/perkins03a.html},
  bibsource = {DBLP, http://dblp.uni-trier.de}
}

@inproceedings{BP14a,
author = {Perozzi, Bryan and Al-Rfou, Rami and Skiena, Steven},
title = {DeepWalk: Online Learning of Social Representations},
year = {2014},
doi = {10.1145/2623330.2623732},
pages = {701--710},
booktitle = {Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)}
}

@inproceedings{BP14a-short,
author = {Perozzi, Bryan and Al-Rfou, Rami and Skiena, Steven},
title = {DeepWalk: Online Learning of Social Representations},
year = {2014},
booktitle = {KDD}
}

@inproceedings{BP17a,
  title={Don't Walk, Skip! Online learning of multi-scale network embeddings},
  author={Perozzi, Bryan and Kulkarni, Vivek and Chen, Haochen and Skiena, Steven},
  booktitle={Proceedings of the IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining},
  pages={258--265},
  year={2017}
}

@inproceedings{MEP18a,
    title = "Deep Contextualized Word Representations",
    author = "Peters, Matthew E.  and
      Neumann, Mark  and
      Iyyer, Mohit  and
      Gardner, Matt  and
      Clark, Christopher  and
      Lee, Kenton  and
      Zettlemoyer, Luke",
    booktitle = "Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL)",
    year = "2018",
    doi = "10.18653/v1/N18-1202",
    pages = "2227--2237"
}

@inproceedings{NP13a,
 author = {Pham, Ninh and Pagh, Rasmus},
 title = {Fast and scalable polynomial kernels via explicit feature maps},
 booktitle = {Proceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining},
 year = {2013},
 pages = {239--247}
} 

@inproceedings{NP13a-short,
 author = {Pham, Ninh and Pagh, Rasmus},
 title = {Fast and scalable polynomial kernels via explicit feature maps},
 booktitle = {KDD},
 year = 2013
}

@inproceedings{XHP08a,
 author = {Xuan-Hieu Phan and Le-Minh Nguyen and Susumu Horiguchi},
 title = {Learning to classify short and sparse text \& web with hidden topics from large-scale data collections},
 booktitle = {Proceedings of the 17th international conference on World Wide Web},
 year = {2008},
 pages = {91--100},
 numpages = {10},
 publisher = {ACM},
} 

@inproceedings{XHP08a-short,
 author = {Xuan-Hieu Phan and Le-Minh Nguyen and Susumu Horiguchi},
 title = {Learning to classify short and sparse text \& web with hidden topics from large-scale data collections},
 booktitle = {WWW},
 year = {2008},
 pages = {91--100}
}

@article{DP21a,
  title={Torch.manual\_seed(3407) is all you need: On the influence of random seeds in deep learning architectures for computer vision}, 
  author={David Picard},
  year={2021},
  eprint={2109.08203},
  archivePrefix={arXiv},
  primaryClass={cs.CV}
}

@Article{SDP97a,
  author = 	 {Della Pietra, Stephen and Della Pietra, Vincent and John Lafferty},
  title = 	 {Inducing features of random fields},
  journal = 	 {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = 	 {1997},
  OPTkey = 	 {},
  volume =	 {19},
  number =	 {4},
  pages =	 {380--393},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@Article{SDP97a-short,
  author = 	 {Della Pietra, Stephen and Della Pietra, Vincent and John Lafferty},
  title = 	 {Inducing features of random fields},
  journal = 	 {IEEE PAMI},
  year = 	 {1997},
  OPTkey = 	 {},
  volume =	 {19},
  number =	 {4},
  pages =	 {380--393},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@inproceedings{IP10a,
	author = {Pil\'{a}szy, Istv\'{a}n and Zibriczky, D\'{a}vid and Tikk, Domonkos},
	title = {Fast {ALS}-based matrix factorization for explicit and implicit feedback datasets},
	booktitle = {Proceedings of the Fourth ACM Conference on Recommender Systems},
	year = {2010},
	pages = {71--78}
} 

@inproceedings{IP10a-short,
	author = {Pil\'{a}szy, Istv\'{a}n and Zibriczky, D\'{a}vid and Tikk, Domonkos},
	title = {Fast {ALS}-based matrix factorization for explicit and implicit feedback datasets},
	booktitle = {RecSys},
	year = {2010},
} 

@article{IP13a,
  title={Threshold optimisation for multi-label classifiers},
  author={Pillai, Ignazio and Fumera, Giorgio and Roli, Fabio},
  journal={Pattern Recognition},
  volume={46},
  number={7},
  pages={2055--2065},
  year={2013}
}

@article{IP17a,
title = {Designing multi-label classifiers that maximize F measures: State of the art},
journal = {Pattern Recognition},
volume = {61},
pages = {394--404},
year = {2017},
author = {Ignazio Pillai and Giorgio Fumera and Fabio Roli}
}

@InProceedings{JP04a,
  author = 	 {Jon Piper and Paul Pauca and Robert Plemmons and Maile Giffin},
  title = 	 {Object Characterization from Spectral Data Using Nonnegative Factorization and Information Theory},
  booktitle = 	 {Proceedings of AMOS Technical Conference},
  OPTcrossref =  {},
  OPTkey = 	 {},
  OPTpages = 	 {},
  year =	 {2004},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTaddress = 	 {},
  OPTmonth = 	 {},
  OPTorganization = {},
  OPTpublisher = {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}


@article{JP07b,
  title={Performance analysis of {MPI} collective operations},
  author={Pje{\v{s}}ivac-Grbovi{\'c}, Jelena and Angskun, Thara and Bosilca, George and Fagg, Graham E. and Gabriel, Edgar and Dongarra, Jack J.},
  journal={Cluster Computing},
  volume={10},
  pages={127--143},
  year={2007}
}

@article{RL75,
author = {R. L. Placket},
journal = {Applied Statistics},
pages = {193--202},
title = {The analysis of permutations},
volume = {24},
year = {1975}
}


@InProceedings{JP98a,
  author = 	 "John C. Platt",
  title = 	 "Fast training of support vector machines using
		  sequential minimal optimization",
  chapter = 	 12,
  year =         {1998},
  editor = 	 {Bernhard Sch\"{o}lkopf and Christopher J. 
		  C. Burges and Alexander J. Smola},
  booktitle = 	 "Advances in Kernel Methods - Support 
		  Vector Learning",
  publisher = 	 "MIT Press",
  address =	 "Cambridge, MA"
}

@InProceedings{JP98a-short,
  author = 	 "John C. Platt",
  title = 	 "Fast training of support vector machines using
		  sequential minimal optimization",
  chapter = 	 12,
  year =         {1998},
  booktitle = 	 "Advances in Kernel Methods - Support 
		  Vector Learning",
  publisher = 	 "MIT Press",
  address =	 "Cambridge, MA"
}



@InProceedings{JP00a,
  author = 	 {J. C. Platt and N. Cristianini and
J. Shawe-Taylor},
  title = 	 {Large Margin {DAG}s for Multiclass
Classification},
  booktitle = 	 {Advances in Neural Information
Processing Systems},
  pages =	 {547--553},
  year =	 {2000},
  volume =	 {12},
  publisher =	 {MIT Press}
}

@InProceedings{JP00a-short,
  author = 	 {J. C. Platt and N. Cristianini and
J. Shawe-Taylor},
  title = 	 {Large Margin {DAG}s for Multiclass
Classification},
  booktitle = 	 {{NIPS} 12},
  year =	 {2000}
}

@inproceedings{JP00b,
  author = "John C. Platt",
  title = "Probabilistic outputs for support vector machines and comparison to regularized
    likelihood methods",
  year = 2000,
  publisher     = {{MIT} Press},
  booktitle     = {Advances in Large Margin Classifiers},
  editor        = {A.J.~Smola and P.L.~Bartlett and B.~Sch{\"o}lkopf and
                  D.~Schuurmans},
  address       = {Cambridge, MA},
}

@article{CP98b,
  title={{An association-based method for automatic indexing with a controlled vocabulary}},
  author={Plaunt, C. and Norgard, B.A.},
  journal={Journal of the American Society for Information Science},
  volume={49},
  number={10},
  pages={888--902},
  year={1998}
}

@article{BP63a,
	title={Gradient methods for minimizing functionals},
	author={Polyak, Boris Teodorovich},
	journal={Zhurnal Vychislitel'noi Matematiki i
		Matematicheskoi Fiziki},
	volume={3},
	number={4},
	pages={643--653},
	year={1963}
}

@article{BTP64,
  title={Some methods of speeding up the convergence of iteration methods},
  author={Polyak, Boris Teodorovich},
  journal={USSR Computational Mathematics and Mathematical Physics},
  volume={4},
  number={5},
  pages={1--17},
  year={1964}
}

@article{BTP64-short,
  title={Some methods of speeding up the convergence of iteration methods},
  author={Polyak, Boris Teodorovich},
  journal={Comput. Math. Math. Phys.},
  volume={4},
  number={5},
  pages={1--17},
  year={1964}
}

@book{BTP87a,
	title={Introduction to Optimization},
	series={Translation Series in Mathematics and Engineering},
	author={Polyak, Boris T.},
	year={1987}
}

@article{BTP90a,
title={A new method of stochastic approximation type},
author={B. T. Polyak},
journal={Avtomat. i Telemekh.},
volume={7},
pages={98--107},
year={1990}
}

@incollection{MP97a,
  author = {Martin Porter},
  title = {An algorithm for suffix stripping},
  booktitle = {Readings in information retrieval},
  year = {1997},
  isbn = {1-55860-454-5},
  pages = {313--316},
  numpages = {4},
  acmid = {275705},
  publisher = {Morgan Kaufmann Publishers Inc.},
  address = {San Francisco, CA, USA},
} 

@incollection{MP97a-short,
  author = {Martin Porter},
  title = {An algorithm for suffix stripping},
  booktitle = {Readings in information retrieval},
  year = {1997},
  pages = {313--316}
}

@TechReport{LFP94a,
        author = {L.F. Portugal and M.G.C. Resende and G. Veiga and 
                  J.J. J\'udice},
        title = {A truncated primal-infeasible dual-feasible 
                 interior point network flow method},
        institution = {AT\&T Labs Research},
        address = {Florham Park, NJ},
        year = {1994},
        }
% checked april 23

@Article{LFP97a,
  author = 	 {L. F. Portugal and F. Bastos
                  J. J. J{\'u}dice 
                  and J. Paix{\~{a}}o and T. Terlaky},
  title = 	 {An investigation of interior-point algorithms for the linear
                   transportation problem},
  journal = 	 {SIAM J. Sci. Comput.},
  year = 	 {1996},
  volume =	 {17},
  number =	 {5},
  pages =	 {1202--1223}
}

@article{SP20a,
  title={Instant{E}mbedding: Efficient Local Node Representations},
  author={Post{\u{a}}varu, {\c{S}}tefan and Tsitsulin, Anton and de Almeida, Filipe Miguel Gon{\c{c}}alves and Tian, Yingtao and Lattanzi, Silvio and Perozzi, Bryan},
  journal={arXiv preprint arXiv:2010.06992},
  year={2020}
}


@TechReport{FAP96,
  author = 	 {Florian A. Potra and Rongqin Sheng},
  title = 	 {Superlinear convergence of interior-point algorithms
                  for semidefinite programming},
  institution =  {Department of Mathematics, The University of Iowa, IA},
  year = 	 {1996},
  number =	 {No. 86/1996},
  note  = {To appear in
{\em J. Optim. Theory Appl.} 99 (1) }
}
% 1998 oct.



@TechReport{FAP97a,
  author = 	 {Florian A. Potra and Rongqin Sheng and Nathan Brixius},
  title = 	 {{SDPHA} -- a {MATLAB} implementation of
   homogeneous interior-point algorithms for semidefinite programming},
  institution =  {Department of Mathematics, The University of Iowa},
  year = 	 {1997},
  address =	 {Iowa City, IA 52242},
  month =	 {April},
  note =	 {Available at http://www.mcs.anl.gov/\~{ }sheng/SDPHA/sdpha.html}
}

		  

@Article{MJDP73a,
  author = 	 "Michael J. D. Powell",
  title = 	 "On search directions for minimization",
  journal =	 "Mathematical Programming",
  year =	 "1973",
  volume =	 "4",
  pages =	 "193--201"
}





@InProceedings{MJD87a,
  author = 	 "M. J. D. Powell",
  editor =	 {J. C. Mason and M. G. Cox},
  booktitle = 	 {Algorithms for approximation},
  publisher = 	 {Clarendon Press},
  year = 	 {1987},
  title = 	 {Radial basis functions for multivariable interpolation: A review},
  address =	 {Oxford}
}

@inproceedings{YP14a,
  author = {Prabhu, Yashoteja and Varma, Manik},
  title = {Fast{XML}: A Fast, Accurate and Stable Tree-classifier for Extreme
Multi-label Learning},
  booktitle = {Proceedings of the 20th ACM SIGKDD International Conference
on Knowledge Discovery and Data Mining (KDD)},
  year = {2014},
  pages = {263--272}
}

@inproceedings{YP14a-short,
  author = {Prabhu, Yashoteja and Varma, Manik},
  title = {Fast{XML}: A Fast, Accurate and Stable Tree-classifier for Extreme
Multi-label Learning},
  booktitle = {KDD},
  year = {2014}
}

@inproceedings{YP18a,
author = {Prabhu, Yashoteja and Kag, Anil and Harsola, Shrutendra and Agrawal, Rahul and Varma, Manik},
title = {Parabel: Partitioned Label Trees for Extreme Classification with Application to Dynamic Search Advertising},
year = {2018},
booktitle = {Proceedings of the 2018 World Wide Web Conference (WWW)},
pages = {993--1002}
}

@incollection{LP12a,
author="Prechelt, Lutz",
editor="Montavon, Gr{\'e}goire
and Orr, Genevi{\`e}ve B.
and M{\"u}ller, Klaus-Robert",
title="Early Stopping --- But When?",
booktitle="Neural Networks: Tricks of the Trade: Second Edition",
year="2012",
publisher="Springer Berlin Heidelberg",
address="Berlin, Heidelberg",
pages="53--67",
doi="10.1007/978-3-642-35289-8_5"
}

@incollection{LP12a-short,
author="Prechelt, Lutz",
title="Early Stopping --- But When?",
booktitle="Neural Networks: Tricks of the Trade: Second Edition",
year="2012",
publisher="Springer Berlin Heidelberg",
pages="53--67"
}

@inproceedings{DP00b,
author = {Precup, Doina and Sutton, Richard S. and Singh, Satinder P.},
title = {Eligibility Traces for Off-Policy Policy Evaluation},
year = {2000},
booktitle = {Proceedings of the Seventeenth International Conference on Machine Learning (ICML)},
pages = {759–766}
}

@book	{WHP92a,
	author = "William H. Press and Brian P. Flannery
		  and Saul A. Teukolsky and William T. Vetterling",
	title = "Numerical Recipes: The Art of Scientific Computing",
	edition = "2nd",
	publisher = "Cambridge University Press",
	address = "Cambridge (UK) and New York",
	year = 1992,
	isbn = "0-521-43064-X",
	}


@InProceedings{DP95a,
  author = 	 {David Price and Stefan Knerr and L\'eon Personnaz and G\'erard Dreyfus},
  title = 	 {Pairwise nerual network classifiers with probabilistic outputs},
  booktitle = 	 {Neural Information Processing Systems},
  pages =	 {1109--1116},
  year =	 {1995},
  publisher = "The {MIT} Press",
  editor =	 {G. Tesauro and D. Touretzky and T. Leen},
  volume =	 {7}
}

@TechReport{DP01a,
  author = {Danil Prokhorov},
  title = {{IJCNN} 2001 Neural Network Competition},
  institution =  {Ford Research Laboratory},
  year = {2001},
  type = {Slide presentation in {IJCNN'01}}
}

@inproceedings{FP00a,
  title={Machine Learning from Imbalanced Data Sets 101},
  author={Provost, Foster},
  booktitle={Proceedings of the AAAI Workshop on Imbalanced Data Sets},
  pages={1--3},
  year={2000},
}

@article{HQ06a,
  title={A quadratically convergent {N}ewton method for computing the nearest correlation matrix},
  author={Qi, Houduo and Sun, Defeng},
  journal={SIAM Journal on Matrix Analysis and Applications},
  volume={28},
  number={2},
  pages={360--385},
  year={2006}
}

@article{HQ06a-short,
  title={A quadratically convergent {N}ewton method for computing the nearest correlation matrix},
  author={Qi, Houduo and Sun, Defeng},
  journal={SIAM J. Matrix Anal. Appl.},
  volume={28},
  number={2},
  pages={360--385},
  year={2006}
}

@article{LQ93a,
  title={Convergence analysis of some algorithms for solving nonsmooth equations},
  author={Qi, Liqun},
  journal={Mathematics of Operations Research},
  volume={18},
  number={1},
  pages={227--244},
  year={1993}
}

@article{LQ93a-short,
  title={Convergence analysis of some algorithms for solving nonsmooth equations},
  author={Qi, Liqun},
  journal={Math. Oper. Res.},
  volume={18},
  number={1},
  pages={227--244},
  year={1993}
}

@article{LQ93b,
  title={A nonsmooth version of {N}ewton's method},
  author={Qi, Liqun and Sun, Jie},
  journal={Mathematical programming},
  volume={58},
  number={1-3},
  pages={353--367},
  year={1993}
}


@article{NQ99a,
  title={On the momentum term in gradient descent learning algorithms},
  author={Qian, Ning},
  journal={Neural networks},
  volume={12},
  number={1},
  pages={145--151},
  year={1999}
}

@article{QT10a,
 author={Qin, Tao and Liu, Tie-Yan and Xu, Jun and Li, Hang},
 title={{LETOR}: A Benchmark Collection for Research on Learning to Rank for Information Retrieval},
 journal={Information Retrieval},
 volume={13},
 number={4},
 pages={346--374},
 year={2010},
 publisher={Springer}
}

@article{HQ18a,
title={{BPRH}: {B}ayesian personalized ranking for heterogeneous implicit feedback},
author={Qiu, Huihuai and Liu, Yun and Guo, Guibing and Sun, Zhu and Zhang, Jie and Nguyen, Hai Thanh},
journal={Information Sciences},
volume={453},
pages={80--98},
year={2018}
}

@inproceedings{JQ18a,
author = {Qiu, Jiezhong and Dong, Yuxiao and Ma, Hao and Li, Jian and Wang, Kuansan and Tang, Jie},
title = {Network Embedding as Matrix Factorization: Unifying {D}eep{W}alk, {LINE}, {PTE}, and {N}ode2vec},
year = {2018},
doi = {10.1145/3159652.3159706},
booktitle = {Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining (WSDM)},
pages = {459–467}
}

@inproceedings{JQ21a,
author = {Qiu, Jiezhong and Dhulipala, Laxman and Tang, Jie and Peng, Richard and Wang, Chi},
title = {Light{NE}: A Lightweight Graph Processing System for Network Embedding},
year = {2021},
booktitle = {Proceedings of the International Conference on Management of Data},
pages = {2281--2289}
}

@inproceedings{JQ19a,
author = {Qiu, Jiezhong and Dong, Yuxiao and Ma, Hao and Li, Jian and Wang, Chi and Wang, Kuansan and Tang, Jie},
title = {Net{SMF}: Large-Scale Network Embedding As Sparse Matrix Factorization},
booktitle = {Proceeding of the World Wide Web Conference (WWW)},
year = {2019}
}

@article{BQ12a,
	author={Bo Qu and Gao Cong and Cuiping Li and Aixin Sun and Hong Chen},
	title={An Evaluation of Classification Models for Question Topic Categorization},
	journal={Journal of the American Society for Information Science and Technology},
	pages={889--903},
	volume={63},
	year={2012}
}

@inproceedings{YQ16a,
  title={Product-based neural networks for user response prediction},
  author={Qu, Yanru and Cai, Han and Ren, Kan and Zhang, Weinan and Yu, Yong and Wen, Ying and Wang, Jun},
  booktitle={Proceedings of IEEE International Conference on Data Mining (ICDM)},
  pages={1149--1154},
  year={2016}
}

@inproceedings{YQ16a-short,
  title={Product-based neural networks for user response prediction},
  author={Qu, Yanru and Cai, Han and Ren, Kan and Zhang, Weinan and Yu, Yong and Wen, Ying and Wang, Jun},
  booktitle={ICDM},
  year={2016}
}

@article{YQ18a,
title={Product-Based Neural Networks for User Response Prediction over Multi-Field Categorical Data},
author={Qu, Yanru and Fang, Bohui and Zhang, Weinan and Tang, Ruiming and Niu, Minzhe and Guo, Huifeng and Yu, Yong and He, Xiuqiang},
journal={ACM Transactions on Information Systems (TOIS)},
volume={37},
number={1},
pages = {5:1--5:35},
year={2018}
}

@article{YQ18a-short,
title={Product-Based Neural Networks for User Response Prediction over Multi-Field Categorical Data},
author={Qu, Yanru and Fang, Bohui and Zhang, Weinan and Tang, Ruiming and Niu, Minzhe and Guo, Huifeng and Yu, Yong and He, Xiuqiang},
journal={ACM TOIS},
volume={37},
pages = {5:1--5:35},
year={2018}
}

@MastersThesis{ZQ22a,
  author = 	 {Zhongyi Que},
  title = 	 {One-class SVM Probabilistic Outputs},
  school = 	 {National Taiwan University},
  year = 	 {2022},
  OPTkey = 	 {},
  OPTtype = 	 {},
  OPTaddress = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@Article{ZQ22b,
  author = 	 {Zhongyi Que and Chih-Jen Lin},
  title = 	 {One-class {SVM} Probabilistic Outputs},
  year = 	 {2024},
  url = {http://www.csie.ntu.edu.tw/~cjlin/papers/oneclass_prob/oneclass_prob.pdf},
  journal={IEEE Transactions on Neural Networks and Learning Systems},
  OPTkey = 	 {},
  OPTtype = 	 {},
  OPTnumber = 	 {},
  OPTaddress = 	 {},
  OPTmonth = 	 {},
  note =	 {To appear},
  OPTannote = 	 {}

}

@book{JRQ92a,
	author = {J. Ross Quinlan},
	title = {C4.5: Programs for Machine Learning},
	publisher = {Morgan Kaufmann},
	year = {1993} }

@Article{LR89a,
  author = "L. Rabiner",
  title = "A Tutorial on Hidden {M}arkov Models and Selected Applications in Speech
    Recognition",
  journal = "Proceedings of the IEEE",
  volume = "77", 
  number="2", 
  pages="257--285", 
  year="1989"
}

@book{LR93a,
  author = {L. Rabiner and B. Juang},
  title = {Fundamentals of Speech Recognition},
  publisher = {Prentice Hall},
  year = {1993}
}

 @Manual{R03a,
       title        = {R: a language and environment for statistical
                       computing},
       author       = {{R Development Core Team}},
       organization = {R Foundation for Statistical Computing},
       address      = {Vienna, Austria},
       year         = 2003,
       note         = {ISBN 3-900051-00-3},
       url          = {http://www.R-project.org}
     }

@inproceedings{KKR11a,
 author = {Rachuri, Kiran K. and Mascolo, Cecilia and Musolesi, Mirco and Rentfrow, Peter J.},
 title = {Sociable{S}ense: exploring the trade-offs of adaptive sampling and computation offloading for social sensing},
 booktitle = {Proceedings of the 17th Annual International Conference on Mobile Computing and Networking},
 year = {2011},
 pages = {73--84}
}

@Misc{AR18b,
  title={Improving language understanding by generative pre-training},
  author={Radford, Alec and Narasimhan, Karthik and Salimans, Tim and Sutskever, Ilya},
  year={2018}
}

@misc{AR19b,
  author = {Radford, Alec and Wu, Jeffrey and Child, Rewon and Luan, David and Amodei, Dario and Sutskever, Ilya},
  title = {Language Models are Unsupervised Multitask Learners},
  year = {2019}
}


@article{AR08b,
 author = {Rahimi, Ali and Recht, Benjamin},
 title = {Random Features for Large-scale Kernel Machines},
 journal = {Advances in Neural Information Processing Systems},
 pages = {1177--1184},
 year = {2008}
}

@article{AR08b-short,
 author = {Rahimi, Ali and Recht, Benjamin},
 title = {Random Features for Large-scale Kernel Machines},
 journal = {NIPS},
 year = {2008}
}

@INPROCEEDINGS {MKR20a,
author = {Md. Khaledur Rahman and Majedul Haque Sujon and Ariful Azad},
booktitle = {Proceedings of IEEE International Conference on Data Mining (ICDM)},
title = {Force2Vec: Parallel Force-Directed Graph Embedding},
year = {2020},
pages = {442-451}
}

@Article{JR96a,
  author = 	 {Jussi Rahola},
  title = 	 {Solution of dense systems of linear equations in the discrete-dipole approximation},
  journal = 	 {SIAM J. Sci. Comput.},
  year = 	 {1994},
  volume =	 {17},
  pages =	 {78--89}
}



@Article{MR97a,
author = 	 {M. Ramana and L. Tun\c{c}el and H. Wolkowicz},
  journal = 	 {SIAM J. Optim.},
  year = 	 {1997},
  volume =	 {7},
  number =	 {3},
  pages =	 {641--662},
  title = 	 {Strong duality for semidefinite programming}
}

@inproceedings{NR15a,
  author = {Nikhil Rao and Hsiang-Fu Yu and Pradeep Ravikumar and Inderjit
S. Dhillon},
  title = {Collaborative Filtering with Graph Information: Consistency and
Scalable Methods},
  booktitle = {Advances in Neural Information Processing Systems 28},
  editor = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and
R. Garnett},
  pages = {2107--2115},
  year = {2015}
}

@inproceedings{NR15a-short,
  author = {Nikhil Rao and Hsiang-Fu Yu and Pradeep Ravikumar and Inderjit
S. Dhillon},
  title = {Collaborative Filtering with Graph Information: Consistency and
Scalable Methods},
  booktitle = {NIPS},
  year = {2015}
}

@INPROCEEDINGS{PR09a,
  author = {Piyush Rai and Hal {Daum\'e III} and Suresh Venkatasubramanian},
  title = {Streamed Learning: One-Pass {SVM}s},
  booktitle = {Proceedings of the Twenty-first International Joint Conference on Artificial Intelligence},
  year = {2009}
}

@INPROCEEDINGS{PR09a-short,
  author = {Piyush Rai and Hal {Daum{\'e} III} and Suresh Venkatasubramanian},
  title = {Streamed Learning: One-Pass {SVM}s},
  booktitle = {IJCAI},
  year = {2009}
}

@article{AR08a,
  title={Simple{MKL}},
  author={Rakotomamonjy, A. and Bach, F. and Canu, S. and Grandvalet, Y.},
  journal={Journal of Machine Learning Research},
  volume={9},
  pages={2491--2521},
  year={2008}
}

@article{SR01a, 
author =
{S. Ramaswamy and P. Tamayo and R. Rifkin and S. Mukherjee and
C.-H.  Yeang and M. Angelo and C. Ladd and M. Reich and
E. Latulippe and J. Mesirov and T. Poggio and W. Gerlad and
M.  Loda and E. Lander and T. Golub}, 
title =
{Multiclass cancer diagnosis using tumor gene expression signatures},
journal = {Proceedings of the National Academy of Science}, 
year = 2001, volume = 98,
number = 26, 
pages = {15149--15154} 
}

@Article{RK67,
  author = {Rao, Pejaver Vishwamber and Kupper, Lawrence L.},
  title = {Ties in paired-comparison experiments: A generalization of the
          {B}radley-{T}erry model},
  journal = {Journal of the American Statistical Association},
  year = {1967},
  volume = {62},
  pages = {194--204},
  note = {[Corrigendum J. Amer. Statist. Assoc. 63 1550-1551]}
}

@misc{AR19a,
      title={Multi-Label Network Classification via Weighted Personalized Factorizations}, 
      author={Ahmed Rashed and Josif Grabocka and Lars Schmidt-Thieme},
      year={2019},
      eprint={1902.09294},
      archivePrefix={arXiv},
      primaryClass={cs.LG}
}

@article{GR14a,
  author  = {Garvesh Raskutti and Martin J. Wainwright and Bin Yu},
  title   = {Early Stopping and Non-parametric Regression: An Optimal Data-dependent Stopping Rule},
  journal = {Journal of Machine Learning Research},
  year    = {2014},
  volume  = {15},
  pages   = {335--366}
}

@article{GR14a-short,
  author  = {Garvesh Raskutti and Martin J. Wainwright and Bin Yu},
  title   = {Early Stopping and Non-parametric Regression: An Optimal Data-dependent Stopping Rule},
  journal = {JMLR},
  volume  = {15},
  pages   = {335--366},
  year    = {2014}
}

@InProceedings{NDR07a,
  author = {Nathan D. Ratliff and J. Andrew Bagnell and Martin A. Zinkevich},
  title = {({O}nline) Subgradient Methods for Structured Prediction},
  booktitle = {Proceedings of the Eleventh International Conference Artificial Intelligence and Statistics (AISTATS)},
  year = {2007},
  pages = {380--387},
  volume = {2}
}

@phdthesis{AR98a,
  title={Maximum Entropy Models For Natural Language Ambiguity Resolution},
  author={Adwait Ratnaparkhi},
  year={1998},
  school={University of Pennsylvania}
}

@Misc{GR99a,
  author =	 {G. R\"{a}tsch},
  title =	 {Benchmark data sets},
  year =	 {1999},
  note =	 {Available at {\tt http://ida.first.gmd.de/\verb"~"raetsch/data/benchmarks.htm}}
}

@incollection{GR02a,
  author    = {Gunnar R\"{a}tsch and Sebastian Mika and Manfred K. Warmuth},
  title     = "On the Convergence of Leveraging",
  booktitle = "Advances in Neural Information Processing Systems 14",
  editor    = "T. G. Dietterich and S. Becker and Z. Ghahramani",
  publisher = "MIT Press",
  address   = "Cambridge, MA",
  pages     = "487--494",
  year      = "2002",
}

@InProceedings{DR04a,
    author = {Deepak Ravichandran and
              Patrick Pantel and
              Eduard Hovy},
    title = {The Terascale Challenge},
    booktitle = {Proceedings of KDD Workshop on Mining for and from the Semantic Web (MSW-04)},
    year = {2004},
    pages = {1--11}
}


@Article{MR97b,
  author = {Macros Raydan},
  title = {The {B}arzilai and {B}orwein Gradient Method for the Large Scale
Unconstrained Minimization Problem},
  journal = {SIAM Journal on Optimization},
  year = {1997},
  pages = {26--33},
  volume = {7}
}

@INPROCEEDINGS{JR08a,
  author={Read, Jesse and Pfahringer, Bernhard and Holmes, Geoff},
  booktitle={Proceedings of IEEE International Conference on Data Mining (ICDM)}, 
  title={Multi-label Classification Using Ensembles of Pruned Sets}, 
  year={2008},
  volume={},
  number={},
  pages={995--1000}
}

@article{JR11a,
  title={Classifier chains for multi-label classification},
  author={Read, Jesse and Pfahringer, Bernhard and Holmes, Geoff and Frank, Eibe},
  journal={Machine learning},
  volume={85},
  pages={333--359},
  year={2011}
}

@article{JR16a,
    author = {Read, Jesse and Reutemann, Peter and Pfahringer, Bernhard and Holmes, Geoff},
    title = {{MEKA}: A Multi-label/Multi-target Extension to {Weka}},
    journal = {Journal of Machine Learning Research},
    year = {2016},
    volume = {17},
    number = {21},
    pages = {1--5}
}

@inproceedings{SJR15a,
	title={On variance reduction in stochastic gradient descent and its asynchronous variants},
	author={Reddi, Sashank J. and Hefny, Ahmed and Sra, Suvrit and Poczos, Barnabas and Smola, Alexander J.},
	booktitle={Advances in Neural Information Processing Systems},
	pages={2647--2655},
	year={2015}
}

@article{SR10a,
 author = {Reddy, Sasank and Mun, Min and Burke, Jeff and Estrin, Deborah and Hansen, Mark and Srivastava, Mani},
 title = {Using Mobile Phones to Determine Transportation Modes},
 journal = {ACM Transactions on Sensor Networks},
 volume = {6},
 number = {2},
 year = {2010},
 pages = {13:1--13:27}
} 

@article{FZ97,
author      = {Franz Rendl and Henry Wolkowicz},
journal     = {Math. Programming},
pages       = {273--299},
title       = {A semidefinite framework for trust region subproblems
               with applications to large scale minimization},
volume      = {77},
year        = {1997}
}


@inproceedings{SR09a,
  title={{BPR}: Bayesian personalized ranking from implicit feedback},
  author={Rendle, Steffen and Freudenthaler, Christoph and Gantner, Zeno and Schmidt-Thieme, Lars},
  booktitle={Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence (UAI)},
  pages={452--461},
  year={2009}
}

@inproceedings{SR09a-short,
  title={{BPR}: Bayesian personalized ranking from implicit feedback},
  author={Rendle, Steffen and Freudenthaler, Christoph and Gantner, Zeno and Schmidt-Thieme, Lars},
  booktitle={UAI},
  year={2009}
}

@inproceedings{SR10b,
  author    = {Steffen Rendle and Lars Schmidt{-}Thieme},
  title     = {Pairwise interaction tensor factorization for personalized tag recommendation},
  booktitle = {Proceedings of the 3rd ACM International Conference on Web Search and Data Mining (WSDM)},
  pages     = {81--90},
  year      = {2010}
}

@inproceedings{SR10b-short,
  author    = {Steffen Rendle and Lars Schmidt{-}Thieme},
  title     = {Pairwise interaction tensor factorization for personalized tag recommendation},
  booktitle = {WSDM},
  year      = {2010}
}

@inproceedings{SR10c,
  title={Factorization machines},
  author={Rendle, Steffen},
  booktitle={Proceedings of IEEE International Conference on Data Mining (ICDM)},
  pages={995--1000},
  year={2010}
}

@inproceedings{SR10c-short,
  title={Factorization machines},
  author={Rendle, Steffen},
  booktitle={ICDM},
  year={2010}
}

@article{SR12a,
    title={Factorization machines with lib{FM}},
    author={Rendle, Steffen},
    journal={ACM Transactions on Intelligent Systems and Technology (TIST)},
    volume={3},
    number={3},
    pages={57},
    year={2012}
}

@article{SR12a-short,
    title={Factorization machines with lib{FM}},
    author={Rendle, Steffen},
    journal={ACM TIST},
    volume={3},
    pages={57},
    year={2012},
}

@inproceedings{SR14a,
  title={Improving pairwise learning for item recommendation from implicit feedback},
  author={Rendle, Steffen and Freudenthaler, Christoph},
  booktitle={Proceedings of the 7th ACM international conference on Web search and data mining (WSDM)},
  pages={273--282},
  year={2014}
}

@inproceedings{SR14a-short,
  title={Improving pairwise learning for item recommendation from implicit feedback},
  author={Rendle, Steffen and Freudenthaler, Christoph},
  booktitle={WSDM},
  year={2014}
}

@article{SR19a,
  title={On the difficulty of evaluating baselines: A study on recommender systems},
  author={Rendle, Steffen and Zhang, Li and Koren, Yehuda},
  journal={arXiv preprint arXiv:1905.01395},
  year={2019}
}


@inproceedings{SR20a,
author = {Rendle, Steffen and Krichene, Walid and Zhang, Li and Anderson, John},
title = {Neural Collaborative Filtering vs. Matrix Factorization Revisited},
year = {2020},
booktitle = {Fourteenth ACM Conference on Recommender Systems},
pages = {240–248}
}

@inproceedings{SR20a-short,
author = {Rendle, Steffen and Krichene, Walid and Zhang, Li and Anderson, John},
title = {Neural Collaborative Filtering vs. Matrix Factorization Revisited},
year = {2020},
booktitle = {RecSys}
}

@InProceedings{PR91a,
  author = 	 {Ph. Refregier and F. Vallet},
  title = 	 {Probabilistic Approach for       
 Multiclass Classification with Neural Networks},
  booktitle = 	 {Proceedings of International Conference   
 on Artificial Networks},
  pages =	 {1003--1007},
  year =	 {1991}
}

@MastersThesis{JR01a,
  author = 	 {Jason D. M. Rennie},
  title = 	 {Improving Multi-class Text Classification with Naive Bayes},
  school = 	 {Massachusetts Institute of Technology},
  year = 	 {2001},
  OPTkey = 	 {},
  OPTtype = 	 {},
  OPTaddress = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}


@techreport{JR01b ,
title = "Improving multiclass text classification with the {S}upport
{V}ector {M}achine",
author = "Jason D. M. Rennie and Ryan Rifkin",
year = {2001},
institution = "Massachusetts Insititute of Technology",
number = "AIM-2001-026",
url = "http://people.csail.mit.edu/jrennie/papers/aimemo2001.pdf" 
}

@techreport{JR01b-short ,
title = "Improving multiclass text classification with the {S}upport
{V}ector {M}achine",
author = "Jason D. M. Rennie and Ryan Rifkin",
year = {2001},
institution = "MIT",
number = "AIM-2001-026",
url = "http://people.csail.mit.edu/jrennie/papers/aimemo2001.pdf" 
}

@techreport{JR05a,
  title={Regularized logistic regression is strictly convex},
  author={Rennie, Jason D. M.},
  year= {2005},
  institution = "MIT",
  url = "http://qwone.com/~jason/writing/convexLR.pdf"
}


@Article{MGCR95,
  author = 	 {M.G.C. Resende and K.G. Ramakrishnan and Z. Drezner},
  title = 	 {Computing lower bounds for the quadratic assignment
                   problem with an interior point algorithm for linear programming},
  journal = 	 {Oper. Res.},
  year = 	 {1995},
  volume =	 {43},
  pages =	 {781--791}
}

@article{BJR00a,
  title={Just-in-time information retrieval agents},
  author={Rhodes, Bradley J. and Maes, Pattie},
  journal={IBM Systems journal},
  volume={39},
  pages={685--704},
  year={2000}
}

@article{BJR00a-short,
  title={Just-in-time information retrieval agents},
  author={Rhodes, Bradley J. and Maes, Pattie},
  journal={IBM Syst. J.},
  volume={39},
  pages={685--704},
  year={2000}
}

@incollection{FR11a,
year={2011},
booktitle={Recommender Systems Handbook},
editor={Ricci, Francesco and Rokach, Lior and Shapira, Bracha and Kantor, Paul B.},
title={Introduction to Recommender Systems Handbook},
publisher={Springer},
author={Ricci, Francesco and Rokach, Lior and Shapira, Bracha},
pages={1--35},
}

@inproceedings{MR07b,
 author = {Richardson, Matthew and Dominowska, Ewa and Ragno, Robert},
 title = {Predicting clicks: estimating the click-through rate for new {AD}s},
 booktitle = {Proceedings of the 16th international conference on World Wide Web},
 year = {2007}
}

@inproceedings{MR07b-short,
 author = {Richardson, Matthew and Dominowska, Ewa and Ragno, Robert},
 title = {Predicting clicks: estimating the click-through rate for new {AD}s},
 booktitle = {WWW},
 year = {2007}
} 


@Article{PR11a,
  author = 	 {Peter Richt\'{a}rik and Martin Tak\'{a}\v{c}},
  title = 	 {Iteration complexity of randomized block-coordinate descent methods for minimizing a composite function},
  year = 	 {2014},
  pages = {1--38},
  volume = {144}, 
  OPTkey = 	 {},
  OPTtype = 	 {},
  OPTnumber = 	 {},
  OPTaddress = 	 {},
  OPTmonth = 	 {},
  journal =	 {Mathematical Programming},
  OPTannote = 	 {}
}



@Article{PR12a,
  author = 	 {Peter Richt\'{a}rik and Martin Tak\'{a}\v{c}},
  title = 	 {Parallel coordinate descent methods for big data optimization},
  journal =	 {Mathematical Programming},
  volume={156},
  number={1-2},
  pages={433--484},
  year={2016},
  OPTkey = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTpages = 	 {},
  OPTmonth = 	 {},
  OPTannote = 	 {}
}

@article{PR12a-short,
  title={Parallel coordinate descent methods for big data optimization},
  author={Richt{\'a}rik, Peter and Tak{\'a}{\v{c}}, Martin},
  journal={Math. Program.},
  volume={156},
  pages={433--484},
  year={2016}
}

@misc{RK13a,
	title={Training neural networks with stochastic {H}essian-free optimization},
	author={Kiros, Ryan},
	note={arXiv preprint arXiv:1301.3641},
	year={2013}
}


@TechReport{RR99a,
  title = 	 {Svm{F}u},
  author =	 {Ryan Rifkin},
  year = {1999},
  note =	 {Software available at {\tt http://five-percent-nation.mit.edu/PersonalPages/rif/SvmFu/index.html}}
}


@article{RR04a,
 author = {Ryan Rifkin and Aldebaro Klautau},
 title = {In Defense of One-Vs-All Classification},
 journal = {Journal of Machine Learning Research},
 volume = {5},
 year = {2004},
 issn = {1533-7928},
 pages = {101--141},
 publisher = {MIT Press},
 address = {Cambridge, MA, USA},
 }

@article{RR04a-short,
 author = {Ryan Rifkin and Aldebaro Klautau},
 title = {In Defense of One-Vs-All Classification},
 journal = {JMLR},
 volume = {5},
 year = {2004},
 issn = {1533-7928},
 pages = {101--141},
 publisher = {MIT Press},
 address = {Cambridge, MA, USA},
 }

@inproceedings{ER95a,
	author = {Ellen Riloff},
	title = {Little words can make a big difference for text classification},
	booktitle = {SIGIR},
	year = {1995},
	pages = {130--136}
} 

@inproceedings{AR18a,
    title = "Few-Shot and Zero-Shot Multi-Label Learning for Structured Label Spaces",
    author = "Rios, Anthony  and
      Kavuluru, Ramakanth",
    booktitle = "Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP)",
    year = "2018",
    doi = "10.18653/v1/D18-1352",
    pages = "3132--3142"
}

@article{GR17a,
    author = {Rizos, Georgios AND Papadopoulos, Symeon AND Kompatsiaris, Yiannis},
    journal = {PLOS ONE},
    title = {Multilabel user classification using the community structure of online networks},
    year = {2017},
    volume = {12},
    pages = {1--34}
}

@article{HR51a,
 author = {Robbins, Herbert and Monro, Sutton},
 title = {A Stochastic Approximation Method},
 journal = {The Annals of Mathematical Statistics},
 volume = {22},
 number = {3},
 pages = {400--407},
 year = {1951}
}

@article{HR51a-short,
 author = {Robbins, Herbert and Monro, Sutton},
 title = {A Stochastic Approximation Method},
 journal = {AMS},
 volume = {22},
 number = {3},
 year = {1951}
}

@article{SMR73a,
  title={Bounds for error in the solution set of a perturbed linear program},
  author={Robinson, Stephen M.},
  journal={Linear Algebra and its applications},
  volume={6},
  pages={69--81},
  year={1973}
}

@article{SMR80,
author      = {S. M. Robinson},
journal     = {Math. Oper. Res.},
pages       = {43--62},
title       = {Strongly regular generalized equations},
volume      = {5},
year        = {1980}
}

@article{AR14a,
	author = {Anderson Rocha and Siome Goldenstein},
	title = {Multiclass from Binary: Expanding One-vs-All, One-vs-One and {ECOC}-based Approaches},
	journal = {IEEE Transactions on Neural Networks and Learning Systems},
	year = {2014},
	volume = {25},
	number={2},
	pages={289--302},
}

@Book{RTR70a,
  author =	 {R. Tyrrell Rockafellar},
  title = 	 {Convex Analysis},
  publisher = 	 {Princeton University Press},
  year = 	 {1970},
  address =	 {Princeton, NJ}
}

@Book{RTR70a-short,
  author =	 {R. Tyrrell Rockafellar},
  title = 	 {Convex Analysis},
  year = 	 {1970}
}

@article{MR01a,
  title={Probability binning comparison: a metric for quantitating univariate distribution differences},
  author={Roederer, Mario and Treister, Adam and Moore, Wayne and Herzenberg, Leonore A},
  journal={Cytometry: The Journal of the International Society for Analytical Cytology},
  volume={45},
  number={1},
  pages={37--46},
  year={2001}
}

@Article{VR85a,
  author = 	 {V. Rokhlin},
  title = 	 {Rapid solution of integral equations of classical potential theory},
  journal = 	 {J. Comput. Phys.},
  year = 	 {1985},
  volume =	 {60},
  pages =	 {187--207}
}

@Article{MR05a,
  title={Dynamic scaling based preconditioning for truncated {N}ewton methods in large scale unconstrained optimization},
  author={Roma, Massimo},
  journal={Optimization Methods and Software},
  volume={20},
  number={6},
  pages={693--713},
  year={2005},
  publisher={Taylor \& Francis}
}

@Article{MR05a-short,
  title={Dynamic scaling based preconditioning for truncated {N}ewton methods in large scale unconstrained optimization},
  author={Roma, Massimo},
  journal={Optim. Methods Softw.},
  volume={20},
  pages={693--713},
  year={2005},
}

@misc{FR16a,
       author = {Roosta-Khorasani, Farbod and Mahoney, Michael W.},
        title = {Sub-Sampled {N}ewton Methods {I}: Globally Convergent Algorithms},
         year = "2016",
	  note={arXiv preprint arXiv:1601.04737}
}

@Article{KR90a,
  author = 	 {K. Rose and F. Gurewitz and G. Fox},
  title = 	 {Statistical mechanics and phase transitions in clustering},
  journal = 	 {Physical Rev. Letters},
  year = 	 {1990},
  volume =	 {65},
  number =	 {8},
  pages =	 {945--948}
}

@Article{KR92a,
  author = 	 {K. Rose and F. Gurewitz and G. Fox},
  title = 	 {Vector quantization by deterministic annealing},
  journal = 	 {IEEE Trans. Inform. Theory},
  year = 	 {1992},
  volume =	 {38},
  pages =	 {1249--1258}
}

@article{PR83a,
title={The central role of the propensity score in observational studies for causal effects},
author={Rosenbaum, Paul R. and Rubin, Donald B.},
journal={Biometrika},
volume={70},
pages={41--55},
year={1983}
}

@inproceedings{NR17a,
title={Predicting counterfactuals from large historical data and small randomized trials},
author={Rosenfeld, Nir and Mansour, Yishay and Yom-Tov, Elad},
booktitle={Proceedings of the 26th International Conference on World Wide Web Companion},
pages={602--609},
year={2017}
}

@inproceedings{NR17a-short,
title={Predicting counterfactuals from large historical data and small randomized trials},
author={Rosenfeld, Nir and Mansour, Yishay and Yom-Tov, Elad},
booktitle={WWW},
year={2017}
}

@article{SR04a,
title = {Boosting as a Regularized Path to a Maximum Margin Classifier},
author = {Saharon Rosset and Ji Zhu and Trevor Hastie},
journal = {Journal of Machine Learining Research},
volume = {5},
pages = {941--973},
year = {2004}
}


@inproceedings{SR05a,
title = {Following Curved Regularized Optimization Solution Paths},
author = {Saharon Rosset},
year = {2005},
pages={1153--1160},
booktitle = {Advances in Neural Information Processing Systems 17},
editor = {Lawrence K. Saul and Yair Weiss and {L\'{e}on} Bottou},
publisher = {MIT Press},
address = {Cambridge, MA}
}

@Article{VR04a,
        author = {Volker Roth},
        title = {The Generalized {LASSO}},
        journal = {IEEE Transactions on Neural Networks},
        year = {2004},
        volume = {15},
        number = {1},
        pages = {16--28}
}

@Misc{JR04a,
  OPTkey = 	 {},
  author =	 {J. Rousu and C. Saunders and S. Szedmak and J. Shawe-Taylor},
  title =	 {On Maximum Margin Hierarchical Classification},
  howpublished = {NIPS workshop on Learning With Structured Outputs
},
  OPTmonth = 	 {},
  year =	 {2004},
  OPTnote = 	 {},
  OPTannote = 	 {}
}



@Book{SR96a,
  author =	 {Sheldon Ross},
  title = 	 {Stochastic Processes},
  publisher = 	 {John Wiley \& Sons, Inc.},
  year = 	 {1996},
  edition =	 {second}
}

@misc{SR16a,
  title={An overview of gradient descent optimization algorithms},
  author={Ruder, Sebastian},
  note={arXiv preprint arXiv:1609.04747},
  year={2016}
}

@inproceedings{GR96a,
    author = {G\"unter Rudolph},
    title = "Convergence of Evolutionary Algorithms in General Search Spaces",
    booktitle = "International Conference on Evolutionary Computation",
    pages = "50--54",
    year = "1996",
    url = "http://citeseer.nj.nec.com/rudolph96convergence.html" 
}

@article{DR86a,
  title={Learning representations by back-propagating errors},
  author={Rumelhart, David E. and Hinton, Geoffrey E. and Williams, Ronald J.},
  journal={Nature},
  volume={323},
  number={6088},
  pages={533--536},
  year={1986}
}

@Misc{SR00a,
  author =	 {Stefan R\"uping},
  title =	 {my{SVM} - another one of those support vector machines},
  year =	 {2000},
  note =	 {Software available at {\tt http://www-ai.cs.uni-dortmund.de/SOFTWARE/MYSVM/}},
}

@article{MER02a,
 author = {Miguel E. Ruiz and Padmini Srinivasan},
 title = {Hierarchical Text Categorization Using Neural Networks},
 journal = {Inf. Retr.},
 volume = {5},
 number = {1},
 year = {2002},
 issn = {1386-4564},
 pages = {87--118},
 doi = {http://dx.doi.org/10.1023/A:1012782908347},
 publisher = {Kluwer Academic Publishers},
 address = {Hingham, MA, USA},
 }


@InProceedings{MR99a,
  author = 	 {Rychetsky, M. and  S. Ortmann and  M. Glesner},
  title = 	 {Construction of a Support Vector Machine
     with Local Experts},
  booktitle = 	 {Workshop on Support
     Vector Machines at the International
     Joint Conference on Artificial
     Intelligence (IJCAI 99)},
  year =	 {1999}
}


@article{YS94,
author      = {Yousef Saad},
title       = {{ILUT}: {A} dual threshold incomplete {LU} factorization},
journal     = {Numer. Linear Algebra Appl.},
volume      = {4},
pages       = {387--402},
year        = {1994}
}


@TechReport{YS94b,
author      = {Yousef Saad},
institution = {Computer Science Department, University of Minnesota},
address     = {Minneapolis, MN 55455},
title       = {{SPARSKIT} : a basic tool kit for sparse matrix computations},
year        = {1994}
}

@inproceedings(YS95a,
title={Preconditioned {Krylov} subspace
methods for {CFD} applications}, author={Y. Saad},
booktitle={Solution Techniques for large-scale {CFD} Problems}, 
publisher={J. Wiley and Sons},editor={W. G. Habashi},
pages={141--157},year={1995})
%%thanks=NSF+NASA                 


@book{YS96,
author      = {Yousef Saad},
publisher   = {PWS Publishing Company},
title       = {Iterative Methods for Sparse Linear Systems},
address     = {Boston},
year        = {1996}
}

@inproceedings{NS20a,
  title={Off-policy bandits with deficient support},
  author={Sachdeva, Noveen and Su, Yi and Joachims, Thorsten},
  booktitle={Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)},
  pages={965--975},
  year={2020}
}

@misc{NS18a,
      title={Medical code prediction with multi-view convolution and description-regularized label-dependent attention}, 
      author={Najmeh Sadoughi and Greg P. Finley and James Fone and Vignesh Murali and Maxim Korenevski and Slava Baryshnikov and Nico Axtmann and Mark Miller and David Suendermann-Oeft},
      year={2018},
      note={arXiv preprint arXiv:1811.01468},
      url       = {http://arxiv.org/abs/1811.01468}           
}

@article{SA10a,
  author = {Ankan Saha and Ambuj Tewari},
  title = {On the nonasymptotic convergence of cyclic coordinate descent methods},
  OPTkey ={},
  OPTmonth ={},
  OPTannote={},
  journal={SIAM Journal on Optimization},
  volume={23},
  number={1},
  pages={576--601},
  year={2013}
}


@article{RS95,
author     = {R. Saigal},
journal    = {Mathematics of Operations Research},
pages      = {570--616},
title      = {An infinitely summable series implementation of interior point
              methods},
volume     = {20},
year       = {1995}
}




@Book{RS95b,
  author = 	 {R. Saigal},
  title = 	 {Linear Programming: A Modern Integrated Analysis},
  publisher = 	 {Kluwer Academic
Publishers},
  year = 	 {1995},
  address =	 {Norwell, MA}
}

@incollection{RS07a,
	title = {{P}robabilistic {M}atrix {F}actorization},
	author = {Ruslan Salakhutdinov and Andriy Mnih},
	booktitle = {Advances in Neural Information Processing Systems 20},
	editor = {J.C. Platt and D. Koller and Y. Singer and S. Roweis},
	publisher = {MIT Press},
	address = {Cambridge, MA},
	pages = {1257--1264},
	year = {2008}
}

@inproceedings{RS07b,
        author = {R. Salakhutdinov and A. Mnih and G. Hinton},
        title = {{R}estricted {B}oltzmann {M}achines for collaborative filtering},
        booktitle = {Proceedings of the 24th international conference on Machine learning},
        year = {2007},
        isbn = {978-1-59593-793-3},
        pages = {791--798},
        location = {Corvalis, Oregon},
        doi = {http://doi.acm.org/10.1145/1273496.1273596},
        publisher = {ACM},
        address = {New York, NY, USA},
}



@Article{GS73a,
  author = 	 {Salton, Gerard and Yang, Chung-Shu},
  title = 	 {On the specification of term values in automatic indexing},
  journal = 	 {Journal of Documentation},
  year = 	 {1973},
  OPTkey = 	 {},
  volume =	 {29},
  OPTnumber = 	 {},
  pages =	 {351--372},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}


@article{GS75a,
 author = {Salton, Gerard and Wong, Anita and  Yang, Chung-Shu},
 title = {A vector space model for automatic indexing},
 journal = {Communications of the ACM},
 volume = {18},
 number = {11},
 year = {1975},
 pages = {613--620}
} 

@article{LDS18a,
author = {Santos, Ludovic Dos and Piwowarski, Benjamin and Denoyer, Ludovic and Gallinari, Patrick},
title = {Representation Learning for Classification in Heterogeneous Graphs with Application to Social Networks},
year = {2018},
volume = {12},
journal = {ACM Transactions on Knowledge Discovery from Data},
articleno = {62},
numpages = {33}
}

@article{GP86a,
title={Partial least-squares regression: a tutorial},
author={Geladi, Paul and Bruce R. Kowalski},
journal={Analytica chimica acta},
volume={185},
pages={1--17},
year={1986},
publisher={Elsevier}
}

@inproceedings{GS88a,
    author = {Gerard Salton and Christopher Buckley},
    title = {Term-weighting approaches in automatic text retrieval},
    booktitle = {Information processing and management 24},
    volume = {5},
    year = {1988},
    pages = {513--523},
    publisher = {}
}

@Book{DS99a,
  ALTauthor = 	 {},
  editor =	 {David Sankoff and Joseph Kruskal},
  title = 	 {Time Warps, String Edits and Macromolecules: The Theory and Practice of Sequence Comparison},
  publisher = 	 {CSLI Publications},
  year = 	 {1999},
  OPTkey = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTaddress = 	 {},
  OPTedition = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@techreport{SAS97,
author      = {S. A. Santos and Danny C. Sorensen},
title       = {A new matrix-free algorithm for the large-scale
               trust-region subproblem},
institution = {Rice University},
number      = {TR95-20},
address     = {Houston, Texas},
type        = {Technical Report},
year        = {1995}
}


@Article{SS00a,
  author =       {Sylvain Sardy and  Andrew G. Bruce and Paul Tseng},
  title =        {Block coordinate relaxation methods for
nonparametric signal denoising with wavelet dictionaries},
  journal =      {Journal of Computational and Graphical Statistics},
  year =         {2000},
  volume =       {9},
  pages =        {361--379}
}

@inproceedings{BS01b,
 author = {Sarwar, Badrul and Karypis, George and Konstan, Joseph and Riedl, John},
 title = {Item-based Collaborative Filtering Recommendation Algorithms},
 booktitle = {Proceedings of the 10th International Conference on World Wide Web},
 year = {2001},
 pages = {285--295}
}

@inproceedings{BS01b-short,
 author = {Sarwar, Badrul and Karypis, George and Konstan, Joseph and Riedl, John},
 title = {Item-based Collaborative Filtering Recommendation Algorithms},
 booktitle = {WWW},
 year = {2001}
}

@TechReport{CS98a,
  author = 	 {C. Saunders and M. O. Stitson and J. Weston and
     L. Bottou and B. Sch\"{o}lkopf and A. Smola},
  title = 	 {Support Vector Machine Reference
     Manual},
  institution =  {Royal Holloway,
     University of London},
  year = 	 {1998},
  number =	 {CSD-TR-98-03},
  address =	 {Egham,
     UK}
}

@InProceedings{CS12a,
  author = 	 {Scherrer, Chad and Halappanavar, Mahantesh and Tewari, Ambuj and Haglin, David},
  title = 	 {Scaling up coordinate descent algorithms for large $\ell_1$ regularization problems},
  year = 	 {2012},
  booktitle =	 {Proceedings of the 29th International Conference on Machine Learning (ICML)},
  url = {},
  OPTkey = 	 {},
  OPTtype = 	 {},
  OPTnumber = 	 {},
  OPTaddress = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}


@InProceedings{CS12a-short,
  author = 	 {Scherrer, Chad and Halappanavar, Mahantesh and Tewari, Ambuj and Haglin, David},
  title = 	 {Scaling up coordinate descent algorithms for large $\ell_1$ regularization problems},
  year = 	 {2012},
  booktitle =	 {ICML}
}

@INPROCEEDINGS{BNS94a,
AUTHOR = {Bill N. Schilit and Norman Adams and Roy Want},
TITLE = {Context-Aware Computing Applications},
BOOKTITLE = {The Workshop on Mobile Computing Systems and Applications},
YEAR = {1994},
}

@article{TS93,
author      = {T. Schlick},
journal     = {SIAM J. Sci. Comput.},
pages       = {424--445},
title       = {Modified {C}holesky factorizations for sparse preconditioners},
volume      = {14},
year        = {1993}
}

@InProceedings{JS19a,
title={Investigating Extensions to Random Walk Based Graph Embedding},
author={J{\"o}rg Schl{\"o}tterer and Martin Wehking and Fatemeh Salehi Rizi and M. Granitzer},
booktitle = {Proceedings of IEEE International Conference on Cognitive Computing},
year={2019},
pages={81-89}
}

@inproceedings{MS07a,
  author = {Mark Schmidt and Glenn Fung and Romer Rosales},
  title = {Fast Optimization Methods for L1 Regularization: A Comparative
Study and Two New Approaches},
  booktitle = {Proceedings of European Conference on Machine Learning},
  year = {2007},
  pages = {286--297}
}

@techreport{MS09a,
author      = {Mark Schmidt and Glenn Fung and Romer Rosales},
title       = {Optimization Methods for L1-Regularization},
institution = {University of British Columbia},
number      = {TR-2009-19},
type        = {Technical Report},
year        = {2009},
}

@article{MS17a,
  title={Minimizing finite sums with the stochastic average gradient},
  author={Schmidt, Mark and Le Roux, Nicolas and Bach, Francis},
  journal={Mathematical Programming},
  volume={162},
  number={1-2},
  pages={83--112},
  year={2017}
}

@article{MS17a-short,
  title={Minimizing finite sums with the stochastic average gradient},
  author={Schmidt, Mark and Le Roux, Nicolas and Bach, Francis},
  journal={Math. Program.},
  volume={162},
  number={1-2},
  pages={83--112},
  year={2017}
}

@article{RBS90,
author      = "R. B. Schnabel and E. Eskow",
title       = "A new modified {C}holesky factorization",
journal     = "SIAM J. Sci. Statist. Comput.",
pages       = "1136--1158",
volume      = "11",
year        = "1990",
}

@inproceedings{TS16a,
 author = {Schnabel, Tobias and Swaminathan, Adith and Singh, Ashudeep and Chandak, Navin and Joachims, Thorsten},
 title = {Recommendations As Treatments: Debiasing Learning and Evaluation},
 booktitle = {Proceedings of the 33rd International Conference on International Conference on Machine Learning (ICML)},
 year = {2016},
 pages = {1670--1679}
}

@inproceedings{TS16a-short,
 author = {Schnabel, Tobias and Swaminathan, Adith and Singh, Ashudeep and Chandak, Navin and Joachims, Thorsten},
 title = {Recommendations As Treatments: Debiasing Learning and Evaluation},
 booktitle = {ICML},
 year = {2016}
}

@inproceedings{JS14a,
  author    = {Johannes Schneider and
               Jasmina Bogojeska and
               Michail Vlachos},
  title     = {Solving Linear SVMs with Multiple 1D Projections},
  booktitle = {Proceedings of the 23rd {ACM} International Conference on Conference
               on Information and Knowledge Management (CIKM)},
  pages     = {221--230},
  year      = {2014}
}





@InProceedings{BS95a,
  author =       {B. Sch\"olkopf and  C. Burges and V. Vapnik},
  title =        {Extracting support data for a given
task},
  booktitle =    {Proceedings of the First
International Conference on Knowledge Discovery  and Data Mining},
  year =         {1995},
  editor =       {U. M. Fayyad and R. Uthurusamy},
  publisher =    {AAAI Press},
  address = {Menlo Park, CA}
}

@PhdThesis{BS97a,
  author = 	 {Bernhard Sch\"{o}lkopf},
  title = 	 "Support Vector Learning",
  year = 	 "1997"
}
%  publisher = 	 "R. Oldenbourg Verlag",
%address =  {Munich},


@TechReport{BS98c,
  author = 	 {Sch\"{o}lkopf, B. and Smola, A. J. and 
     Williamson, R. and Bartlett, P.},
  title = 	 {New Support Vector
     Algorithms},
  institution =  {Royal Holloway,
     University of London},
  year = 	 {1998},
  type =	 {Neuro COLT
     Technical Report},
  number =	 {TR-1998-031},
  address =	 {Egham,
     UK}
}


@InProceedings{BS99a,
  author = 	 {Sch\"{o}lkopf, B. and Smola, A. J. and 
     Williamson, R.},
  title = 	 {Shrinking
     the Tube: A New Support Vector Regression
     Algorithm},
  booktitle = 	 {Advances in Neural Information Processing
     Systems},
  year =	 {1999},
  editor =	 {M. S. Kearns and
     S. A. Solla and D. A. Cohn},
  volume =	 {11},
  address =      {Cambridge,
     MA},
  publisher =	 {MIT Press}
}


@Article{BS99b,
  author        = {Bernhard Sch\"olkopf and John C. Platt and John Shawe-Taylor and Alexander J.
                  Smola and Robert C. Williamson},
  title         = {Estimating the Support of a High-Dimensional
                  Distribution},
  journal = {Neural Computation},
  volume = {13},
  number = {7},
 pages  = {1443--1471},
  year          = {2001}
}


@Article{BS99b-short,
  author        = {Bernhard Sch\"olkopf and John C. Platt and John Shawe-Taylor and Alexander J.
                  Smola and Robert C. Williamson},
  title         = {Estimating the Support of a High-Dimensional
                  Distribution},
  journal = {Neural Comput.},
  volume = {13},
 pages  = {1443--1471},
  year          = {2001}
}

@article{BS00a,
   author    = {B. Sch\"{o}lkopf and A.~Smola and R.~C.~Williamson and
P.~L.~Bartlett},
   title     = {New Support Vector Algorithms},
   journal   = "Neural Computation",
   volume    = "12",
   issue     = "5",
   pages     = {1207--1245},
   year      = 2000}

@inproceedings{BS00b,
    author = {Bernhard Sch\"{o}lkopf},
    title = {The Kernel Trick for Distances},
    booktitle = "{NIPS}",
    pages = "301--307",
    year = "2000"
}

@inproceedings{BS00c,
  author = {Sch\"{o}lkopf, Bernhard and Williamson, Robert C and Smola, Alex and Shawe-Taylor, John and Platt, John},
  booktitle = {Advances in Neural Information Processing Systems},
  title = {Support Vector Method for Novelty Detection},
  year = {2000}
}

@inproceedings{BS00c-short,
  author = {Sch\"{o}lkopf, Bernhard and Williamson, Robert C and Smola, Alex and Shawe-Taylor, John and Platt, John},
  booktitle = {NIPS},
  title = {Support Vector Method for Novelty Detection},
  year = {2000}
}

@inproceedings{BS01a,
    author = {Bernhard Sch\"{o}lkopf and Ralf Herbrich and
	Alex J. Smola},
    title = {A Generalized Representer Theorem},
  	booktitle = {Proceedings of the 14th Annual Conference
	on Computational Learning Theory and the 5th European
	Conference on Computational Learning Theory},
    pages = "416--426",
    year = "2001"
}

@inproceedings{BS01a-short,
    author = {Bernhard Sch\"{o}lkopf and Ralf Herbrich and
	Alex J. Smola},
    title = {A Generalized Representer Theorem},
    booktitle = {COLT},
    year = "2001"
}

@Book{BS02a,
  author =	 {Bernhard Sch\"{o}lkopf and Alexander J. Smola},
  title = 	 {Learning with kernels},
  publisher = 	 {MIT Press},
  year = 	 {2002},
}

@article{BS97b,
  author = {B. Sch\"{o}lkopf and K.-K. Sung and C. J.
	      C. Burges and F. Girosi and P. Niyogi and T.
	      Poggio and V. Vapnik},
  title = {Comparing support vector machines
	with {G}aussian kernels to radial basis
	    function classiers},
  journal = {IEEE Transactions on
	      Signal Processing},
  volume = {45},
  number={11},
  pages = {2758--2765},
  year = {1997},
  url = {http://citeseer.nj.nec.com/article/sch97comparing.html}
}

%S. Scholtes, Introduction to piecewise differentiable equations,
Habilitationsschrift, Institut
%f罕r Statistik und Mathematische Wirtschaftstheorie, Universit災t
Karlsruhe, Karlsruhe,
%Germany, 1994.
%
% I don't know if it is a thesis

@PhdThesis{SS94a,
  author = 	 {S. Scholtes},
  title = 	 {Introduction to piecewise differentiable equations},
  school = 	 {University of Karlsruhe},
  year = 	 1994
}

@Article{NNS99a,
  author =   {Nicol N. Schraudolph},
  title =    {A Fast, Compact Approximation of the Exponential Function},
  journal = {Neural Computation},
  volume={11},
  pages={853--862},
  year =     {1999}
}

@article{NNS02a,
  title={Fast curvature matrix-vector products for second-order gradient descent},
  author={Schraudolph, Nicol N.},
  journal={Neural Computation},
  volume={14},   
  number={7},    
  pages={1723--1738},
  year={2002}
}

@article{NNS02a-short,
  title={Fast curvature matrix-vector products for second-order gradient descent},
  author={Schraudolph, Nicol N.},
  journal={Neural Comput.},
  volume={14},   
  pages={1723--1738},
  year={2002}
}

@InProceedings{NNS07a,
  author =       {Nicol N. Schraudolph and Jin Yu and Simon Gunter},
  title =        {A Stochastic Quasi-{N}ewton Method for Online Convex Optimization},
  booktitle =    {Proceedings of the 11th International Conference Artificial Intelligence and Statistics (AISTATS)},
  year =         {2007},
  pages =        {433--440}
}

@inproceedings{ES22a,
  title={On missing labels, long-tails and propensities in extreme multi-label classification},
  author={Schultheis, Erik and Wydmuch, Marek and Babbar, Rohit and Dembczynski, Krzysztof},
  booktitle={Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)},
  pages={1547--1557},
  year={2022}
}


@article{AS97,
author      = {A. Schwartz and E. Polak},
title       = {Family of projected descent methods for optimization
               problems with simple bounds},
journal     = {J. Optim. Theory Appl.},
pages       = {1--31},
volume      = {92},
year        = {1997}
}


@INPROCEEDINGS{DS07a,
  author = {D. Sculley and Gabriel M. Wachman},
  title = {Relaxed Online SVMs for Spam Filtering},
  booktitle = {SIGIR},               
  year = {2007}                     
}                

@incollection{DS09a,
 author={D. Sculley},
 title={Large Scale Learning to Rank},
 booktitle={NIPS 2009 Workshop on Advances in Ranking},
 year={2009}
}

@incollection{DS15a,
title = {Hidden Technical Debt in Machine Learning Systems},
author = {Sculley, D. and Holt, Gary and Golovin, Daniel and Davydov, Eugene and Phillips, Todd and Ebner, Dietmar and Chaudhary, Vinay and Young, Michael and Crespo, Jean-Fran\c{c}ois and Dennison, Dan},
booktitle = {Advances in Neural Information Processing Systems 28},
pages = {2503--2511},
year = {2015}
}

@incollection{DS15a-short,
title = {Hidden Technical Debt in Machine Learning Systems},
author = {Sculley, D. and Holt, Gary and Golovin, Daniel and Davydov, Eugene and Phillips, Todd and Ebner, Dietmar and Chaudhary, Vinay and Young, Michael and Crespo, Jean-Fran\c{c}ois and Dennison, Dan},
booktitle = {NIPS},
year = {2015}
}

@TechReport{MKS88,
  author = 	 {Mark K. Seager},
  title = 	 {A {SLAP} for the masses},
  institution =  {Lawrence Livermore National Laboratory},
  year = 	 {1988},
  type =         {Technical Report},
  number = 	 {UCRL-100267},
  address = 	 {Livermore, California},
  month = 	 {December}
}

@article{FS02a,
  title={Machine learning in automated text categorization},
  author={Fabrizio Sebastiani},
  journal={ACM Comput. Surv.},
  volume={34},
  number={1},
  pages={1--47},
  year={2002}
}

@misc{AMCS13a,
title={Non-Asymptotic Convergence Analysis of Inexact Gradient Methods for
Machine Learning Without Strong Convexity},
author={So, Anthony Man-Cho},
note={arXiv preprint arXiv:1309.0113},
year={2013}
}


@inproceedings{BS13a,
author = {Solecki, Benjamin and Silva, Lucas and Efimov, Dmitry},
title = {{KDD} {C}up 2013: author disambiguation},
booktitle = {Proceedings of the KDD Cup 2013 Workshop},
pages = {9:1--9:3},
year = {2013},
publisher = {ACM},
} 

@InProceedings{MS00a,
  author = "M. Seeger",
  title = "Bayesian model selection for Support Vector machines",
  booktitle = 	 {Advances in Neural Information Processing Systems},
  OPTcrossref =  {},
  OPTkey = 	 {},
  pages =	 {603--609},
  year =	 {2000},
  editor =	 {Sara A. Solla and Todd K. Leen and Klaus-Robert M{\"u}ller},
  volume =	 {12},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTaddress = 	 {},
  OPTmonth = 	 {},
  OPTorganization = {},
  OPTpublisher = {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@article{LS1874a,
  title={Ueber ein Verfahren, die Gleichungen, auf welche die Methode der kleinsten Quadrate f{\"u}hrt, sowie line{\"a}re Gleichungen {\"u}berhaupt, durch successive Ann{\"a}herung aufzul{\"o}sen},
  author={Seidel, Ludwig},
  year={1874},
  journal={Abhandlungen der Bayerischen Akademie der Wissenschaften.
Mathematisch-Naturwissenschaftliche Abteilung},
  volume={11},
  number = {3},
  pages={81--108}
}


@InProceedings{MS99a,
  author = 	 {Mathini Sellathurai and Simon Haykin},
  title = 	 {The Separability Theory Of Hyperbolic Tangent Kernels And Support Vector Machines For Pattern Classification  },
  booktitle = 	 {Proceedings of ICASSP99},
  year =	 {1999}
}
@Article{TS05a,
  author = {Thomas Serafini and Gaetano Zanghirati and Luca Zanni},
  title = {Gradient projection methods for quadratic programs and
applications in training support vector machines},
  journal = {Optimization Methods and Software},
  year = {2005},
  pages = {353--378},
  volume = {20}
}

@article{TS05b,
	author={Thomas Serafini and Luca Zanni},
	title = {On the Working Set Selection in Gradient Projection-based
Decomposition Techniques for Support Vector Machines},
	journal = {Optimization Methods and Software},
	volume={20},
	pages={583--596},
	year={2005}
}


@inproceedings{PS12a,
   title={Convolutional neural networks applied to house numbers digit  
classification},
   author={Sermanet, Pierre and Chintala, Soumith and {LeCun}, Yann},
   booktitle={Proceedings of the 21st International  
Conference on Pattern Recognition (ICPR), 2012 },
   pages={3288--3291},
   year={2012}
}

@article{HSS92a,
 author = {H. Sebastian Seung and Manfred Opper and Haim Sompolinsky},
 title = {Query by Committee},
 journal = {Proceedings of the Fifth Workshop on Computational Learning Theory},
 pages = {287--294},
 year = {1992},
}


@Article{RES00a,
  author = 	 {Robert E. Schapire and Yoram Singer},
  title = 	 {BoosTexter: A Boosting-based System for Text
Categorization},
  journal = 	 {Machine Learning},
  year = 	 2000,
  volume =	 39,
  number =	 {2/3},
  pages =	 {135--168}
}

@article{TS20a,
  title={The effects of randomness on the stability of node embeddings},
  author={Schumacher, Tobias and Wolf, Hinrikus and Ritzert, Martin and Lemmerich, Florian and Bachmann, Jan and Frantzen, Florian and Klabunde, Max and Grohe, Martin and Strohmaier, Markus},
  journal={arXiv preprint arXiv:2005.10039},
  year={2020}
}


@inproceedings{TS13a,
author = {Schaul, Tom and Zhang, Sixin and {LeCun}, Yann},
booktitle = {Proceedings of the 30th Annual International Conference on Machine Learning},
pages = {343--351},
title = {No more pesky learning rates},
year = {2013}
}

@inproceedings{TS13a-short,
author = {Schaul, Tom and Zhang, Sixin and {LeCun}, Yann},
booktitle = {ICML},
pages = {343--351},
title = {No more pesky learning rates},
year = {2013}
}

@Article{NS10a,
  author = 	 {Nicola Segata and Enrico Blanzieri},
  title = 	 {Fast and Scalable Local Kernel Machines},
  journal = {Journal of Machine Learning Research},
  year = 	 {2010},
  OPTkey = 	 {},
  volume =	 {11},
  OPTnumber = 	 {},
  pages =	 {1883--1926},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@InProceedings{FS03a,
  author    = {Fei Sha and
               Fernando C. N. Pereira},
  title     = {Shallow Parsing with Conditional Random Fields},
  booktitle = {Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology (NAACL)},
  pages     = {134--141},
  year      = {2003}
}

@inproceedings{SSS07a,
   title={Pegasos: primal estimated sub-gradient solver for {SVM}},
   author={Shai Shalev-Shwartz and Yoram Singer and Nathan Srebro},
   booktitle = {Proceedings of the Twenty Fourth International Conference on
                Machine Learning (ICML)},
   pages={},
   year={2007}
}


@inproceedings{SSS07a-short,
  title={Pegasos: primal estimated sub-gradient solver for {SVM}},
  author={S. Shalev-Shwartz and Y. Singer and N. Srebro},
  booktitle = {ICML},
  year={2007}
}

@inproceedings{SSS09a,
  author = {Shai Shalev-Shwartz and Ambuj Tewari},
  title = {Stochastic Methods for L1 Regularized Loss Minimization},
  booktitle = {Proceedings of the Twenty Sixth International Conference
on Machine Learning (ICML)},
  year = {2009}
}

@article{SSS11a,
   title={Pegasos: primal estimated sub-gradient solver for {SVM}},
   author={Shai Shalev-Shwartz and Yoram Singer and Nathan Srebro},
   journal = {Mathematical Programming},
   pages={3--30},
   year={2011},
   number={1},
   volume={127}
}

@article{SSS11a-short,
   title={Pegasos: primal estimated sub-gradient solver for {SVM}},
   author={Shai Shalev-Shwartz and Yoram Singer and Nathan Srebro},
   journal = {Math. Programming},
   pages={3--30},
   year={2011},
   number={1},
   volume={127}
}


@article{SSS11b,
  author = {Shai Shalev-Shwartz and Ambuj Tewari},
  title = {Stochastic Methods for l1-Regularized Loss Minimization},
  journal = {Journal of Machine Learning Research},
  year = 	 {2011},
  OPTkey = 	 {},
  volume =	 {12},
  OPTnumber = 	 {},
  pages =	 {1865--1892}
}

@article{SSS11b-short,
  author = {Shai Shalev-Shwartz and Ambuj Tewari},
  title = {Stochastic Methods for l1-Regularized Loss Minimization},
  journal = {JMLR},
  year = 	 {2011},
  volume =	 {12},
  pages =	 {1865--1892}  
}


@article{SSS12a ,
  author = 	 {Shai Shalev-Shwartz and Tong Zhang},
  title =	{Stochastic Dual Coordinate Ascent Methods for Regularized Loss Minimization},
  journal =	{Journal of Machine Learning Research},
  volume ={14},
  pages ={567--599},
  year ={2013}
}

@article{SSS12a-short,
  author = 	 {Shai Shalev-Shwartz and Tong Zhang},
  title =	{Stochastic Dual Coordinate Ascent Methods for Regularized Loss Minimization},
  journal =	{JMLR},
  volume ={14},
  pages ={567--599},
  year ={2013}
}

@misc{SSS13a,
title={Accelerated Proximal Stochastic Dual Coordinate Ascent for Regularized
Loss Minimization},
author={Shalev-Shwartz, Shai and Zhang, Tong},
note={arXiv preprint arXiv:1309.2375},
year={2013}
}


@article{DFS70a,
    title={Conditioning of quasi-{N}ewton methods for function
        minimization},
    author={Shanno, David F},
    journal={Mathematics of Computation},
    volume={24},
    number={111},
    pages={647--656},
    year={1970}
}

@Article{JST98a,
  author = 	 {John Shawe-Taylor and Peter L. Bartlett and Robert
C. Williamson and Martin Anthony},
  title = 	 {Structural Risk Minimization Over Data-Dependent
Hierachies},
  journal = 	 {IEEE Transactions on Information Theory},
  year = 	 {1998},
  volume =	 {44},
  pages =	 {1926--1940},
}

@article{NS19a,
  title={{GAT2VEC}: representation learning for attributed graphs},
  author={Sheikh, Nasrullah and Kefato, Zekarias and Montresor, Alberto},
  journal={Computing},
  volume={101},
  pages={187--209},
  year={2019}
}

@Misc{SS04a,
  title = 	 {\url{http://www.simonshepherd.supanet.com/nnmf.htm}},
  OPTkey = 	 {},
  author =	 {Simon Shepherd},
  OPTorganization = {},
  OPTaddress = 	 {},
  OPTedition = 	 {},
  OPTmonth = 	 {},
  year =	 {2004},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@article{SKS03a,
  title={A simple and efficient algorithm for gene selection using
sparse logistic regression},
  author={Shevade, Shirish Krishnaj and Keerthi, S. Sathiya},
  journal={Bioinformatics},
  volume={19},
  number={17},
  pages={2246--2253},
  year={2003}
}

@inproceedings{DS11a,
author = {Shen, Dan and Ruvini, Jean David and Somaiya, Manas and Sundaresan, Neel},
title = {Item categorization in the e-commerce domain},
year = {2011},
booktitle = {Proceedings of the 20th ACM International Conference on Information and Knowledge Management (CIKM)},
pages = {1921--1924}
}

@inproceedings{DS11a-short,
 author = {Dan Shen and Jean David Ruvini and Manas Somaiya and Neel Sundaresan},
 title = {Item categorization in the e-commerce domain},
 booktitle = {CIKM},
 year = {2011},
 pages = {1921--1924}
}



@InProceedings{DS12a,
  author = 	 {Dan Shen and Jean-David Ruvini and Badrul Sarwar},
  title = 	 {Large-scale Item Categorization for e-Commerce},
 booktitle = {Proceedings of the 21st ACM international conference on Information and knowledge management (CIKM)},
 year = {2012},
 pages = {595--604}
}

@article{JS50a,
	Title={Adjustment of an inverse matrix corresponding to a change
		in one element of a given matrix},
	Author={Sherman, Jack and Morrison, Winifred J},
	Journal={The Annals of Mathematical Statistics},
	Volume={21},
	Number={1},
	Pages={124--127},
	Year={1950}
}


@misc{HS17a,
      title={Towards Automated {ICD} Coding Using Deep Learning}, 
      author={Haoran Shi and Pengtao Xie and Zhiting Hu and Ming Zhang and Eric P. Xing},
      year={2017},
      url={http://arxiv.org/abs/1711.04075},
      note={arXiv preprint arXiv:1711.04075}
}

@article{JS00a,
    author = "Jianbo Shi and Jitendra Malik",
    title = "Normalized Cuts and Image Segmentation",
    journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence",
    volume = "22",
    number = "8",
    pages = "888--905",
    year = "2000"
}


@Article{JS09a,
        author = {Jianing Shi and Wotao Yin and Stanley Osher and Paul
Sajda},
        title = {A Fast Hybrid Algorithm for Large Scale l1-Regularized
Logistic Regression},
        journal = {Journal of Machine Learning Research},
        volume = {11},
        pages = {713--741},
        year = {2010}
}


@article{QS09a,
 author = {
Qinfeng Shi and  James Petterson and Gideon Dror and  John Langford
and  Alex Smola and  S.V.N. Vishwanathan},
 title = {Hash Kernels for Structured Data},
 journal = {Journal of Machine Learning Research},
 volume = {10},
 year = {2009},
 pages = {2615--2637}
 }


@inproceedings{QS09b,
 author = {Qinfeng Shi and James Petterson and Gideon Dror and John
Langford and Alex Smola and Alex Strehl and S.V.N. Vishwanathan},
 title = {Hash Kernels},
 booktitle = {JMLR Workshop and Conference Proceedings: Proceedings of the Twelfth International Conference on Artificial Intelligence and Statistics},
 volume = {5},
 pages = {496--503},
 year = {2009}
}

@InProceedings{SS97a,
  author = "S. Shi and A. Weigend",
  title = "Taking Time Seriously: Hidden {M}arkov Experts Applied to Financial Engineering",
  booktitle = 	 {CIFEr '97: Proc. of the Conf. on Computational
    Intelligence for Financial Engineering},
    publisher =	 {IEEE},
  pages =	 {244--252},
  year = "1997" 
}

@inproceedings{YS12a,
    title={{TFMAP}: optimizing {MAP} for top-n context-aware recommendation},
    author={Shi, Yue and Karatzoglou, Alexandros and Baltrunas, Linas and Larson, Martha and Hanjalic, Alan and Oliver, Nuria},
    booktitle={Proceedings of the 35th international ACM SIGIR conference on Research and development in information retrieval},
    pages={155--164},
    year={2012}
}

@inproceedings{YS12a-short,
    title={{TFMAP}: optimizing {MAP} for top-n context-aware recommendation},
    author={Shi, Yue and Karatzoglou, Alexandros and Baltrunas, Linas and Larson, Martha and Hanjalic, Alan and Oliver, Nuria},
    booktitle={SIGIR},
    year={2012}
}

@article{AS05a,
	title={Incremental training of support vector machines},
	author={Shilton, Alistair and Palaniswami, Marimuthu and Ralph, Daniel and Tsoi, Ah Chung},
	journal={IEEE Transactions on Neural Newtorks},
	volume={16},
	number={1},
	pages={114--131},
	year={2005}
}
@article{AS05a-short,
	title={Incremental training of support vector machines},
	author={Shilton, Alistair and Palaniswami, Marimuthu and Ralph, Daniel and Tsoi, Ah Chung},
	journal={IEEE TNN},
	volume={16},
	pages={114--131},
	year={2005}
}

@article{HJS05a,
  title={One-class Support Vector Machines -- An Application in Machine Fault Detection and Classification},
  author={Shin, Hyun Joon and Eom, Dong-Hwan and Kim, Sung-Shick},
  journal={Computers and Industrial Engineering},
  volume={48},
  number={2},
  pages={395--408},
  year={2005},
  publisher={Elsevier}
}

@inproceedings{MS15a,
 author = {Shokouhi, Milad and Guo, Qi},
 title = {From Queries to Cards: Re-ranking Proactive Card Recommendations Based on Reactive Search History},
 booktitle = {Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval},
 year = {2015},
 pages = {695--704}
}

@inproceedings{MS15a-short,
 author = {Shokouhi, Milad and Guo, Qi},
 title = {From Queries to Cards: Re-ranking Proactive Card Recommendations Based on Reactive Search History},
 booktitle = {SIGIR},
 year = {2015}
}

@inproceedings{AS14a,
 title = {Asymmetric {LSH} {(ALSH)} for Sublinear Time Maximum
Inner Product Search {(MIPS)}},
 author = {Anshumali Shrivastava and Ping Li},
 booktitle = {Advances in Neural Information Processing Systems
27},
 editor = {Z. Ghahramani and M. Welling and C. Cortes and N.D.
Lawrence and K.Q. Weinberger},
 pages = {2321--2329},
 year = {2014},
}

@inproceedings{AS14a-short,
 title = {Asymmetric {LSH} {(ALSH)} for Sublinear Time Maximum
Inner Product Search {(MIPS)}},
 author = {Anshumali Shrivastava and Ping Li},
 booktitle = {NIPS},
 editor = {Z. Ghahramani and M. Welling and C. Cortes and N.D.
Lawrence and K.Q. Weinberger},
 pages = {2321--2329},
 year = {2014},
}

@misc{IS23a,
      title={The Curse of Recursion: Training on Generated Data Makes Models Forget}, 
      author={Ilia Shumailov and Zakhar Shumaylov and Yiren Zhao and Yarin Gal and Nicolas Papernot and Ross Anderson},
      year={2023},
      eprint={2305.17493},
      archivePrefix={arXiv},
      primaryClass={cs.LG}
}

@inproceedings{KS10a,
 author = {Shvachko, Konstantin and Kuang, Hairong and Radia, Sanjay and Chansler, Robert},
 title = {The Hadoop Distributed File System},
 booktitle = {Proceedings of the 2010 IEEE 26th Symposium on Mass Storage Systems and Technologies (MSST)},
 year = {2010},
 pages = {1--10}
}


@inproceedings{KS10a-short,
 author = {Shvachko, Konstantin and Kuang, Hairong and Radia, Sanjay and Chansler, Robert},
 title = {The Hadoop Distributed File System},
 booktitle = {MSST},
 year = {2010}
}

@Article{GPS47a,
    author = {Sillitto, G. P.},
    title = {The distribution of {K}endall's $\tau$ coefficient of rank 
correlation in rankings containing ties},
    journal = {Biometrika},
    year = {1947},
    volume = {34},
    pages = {36--40}
}


@InProceedings{HUS04a,
  author = 	 {Hans Ulrich Simon},
  title = 	 {On the Complexity of Working Set Selection},
  booktitle = 	 {
Proceedings of the 15th International Conference
on Algorithmic Learning Theory (ALT 2004)},
  OPTcrossref =  {},
  OPTkey = 	 {},
  OPTpages = 	 {},
  year =	 {2004},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTaddress = 	 {},
  OPTmonth = 	 {},
  OPTorganization = {},
  OPTpublisher = {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@Article{GS99a,
  author = 	 {G. Simons and Y.-C. Yao},
  title = 	 {Asymptotics when the number of parameters tends to
  infinity in the {B}radley-{T}erry model for paired comparisons},
  journal = 	 {The Annals of Statistics},
  year = 	 1999,
  volume =	 27,
  number =	 3,
  pages =	 {1041--1060}
}

@inproceedings{KS14a,
  author    = {Karen Simonyan and Andrew Zisserman},
  title     = {Very Deep Convolutional Networks for Large-Scale Image Recognition},
  booktitle = {Proceedings of the 3rd International Conference on Learning Representations (ICLR)},
  year      = {2015}
}


@Book{PS02a,
  editor =	 {Peter Sin{\v c}\'ak and Jens Strackeljan and Michal Kolcun and Daniel Novotn\'y and Peter Szathm\'ary},
  title = 	 {Electricity Load Forcast Using Intelligent Technologies},
  booktitle = 	 {Electricity Load Forcast Using Intelligent Technologies},
  publisher = 	 {{EUNITE}: The European Network on Intelligent Technologies for Smart Adaptive Systems},
  year = 	 {2002}
}

@Article{VS06a,
  author = 	 {Vikas Sindhwani and S. Sathiya Keerthi},
  title = 	 {Large Scale Semisupervised Linear {SVM}s},
  journal = 	 {29th Annual International ACM SIGIR},
  year = 	 {2006}
}

@inproceedings{VS09a,
  title={A family of non-negative matrix factorizations for one-class collaborative filtering problems},
  author={Vikas Sindhwani and Serhat S. Bucak and Jianying Hu and Aleksandra Mojsilovic},
  booktitle={Proceedings of the ACM Recommender Systems Conference (RecSys)},
  year={2009}
}

@inproceedings{VS09a-short,
  title={A family of non-negative matrix factorizations for one-class collaborative filtering problems},
  author={Vikas Sindhwani and Serhat S. Bucak and Jianying Hu and Aleksandra Mojsilovic},
  booktitle={RecSys},
  year={2009}
}

@INPROCEEDINGS{VS10a,
    author = {Vikas Sindhwani and Serhat S Bucak and Jianying Hu and
Aleksandra Mojsilovic},
    title = {One-Class Matrix Completion with Low-Density Factorizations},
 booktitle = {Proceedings of the IEEE International Conference on Data
Mining (ICDM)},
    year = {2010},
    pages = {1055--1060}
}

@INPROCEEDINGS{VS10a-short,
    author = {Vikas Sindhwani and Serhat S. Bucak and Jianying Hu and
Aleksandra Mojsilovic},
    title = {One-Class Matrix Completion with Low-Density Factorizations},
    booktitle = {ICDM},
    year = {2010}
}

@inproceedings{US19a,
  title     = {Node Embedding over Temporal Graphs},
  author    = {Singer, Uriel and Guy, Ido and Radinsky, Kira},
  booktitle = {Proceedings of the Twenty-Eighth International Joint Conference on
               Artificial Intelligence (IJCAI)},
  pages     = {4605--4612},
  year      = {2019}
}

@inproceedings{APS08a,
  title={Relational learning via collective matrix factorization},
  author={Ajit P. Singh and Geoffrey J. Gordon},
  booktitle={Proceedings of the 14th ACM SIGKDD international conference on
Knowledge discovery and data mining (KDD)},
  pages={650--658},
  year={2008}
}

@inproceedings{APS08a-short,
  title={Relational learning via collective matrix factorization},
  author={Ajit P. Singh and Geoffrey J. Gordon},
  booktitle={KDD},
  year={2008}
}

@article{TFS81a,
    author = "T. F. Smith and M. S. Waterman",
    title = "Identification of common molecular subsequences",
    journal = "Journal of Molecular Biology",
    volume = "147",
    pages = "195--197",
    year = "1981",
    url = "citeseer.nj.nec.com/smith81identification.html" }
}


@inproceedings{AJS00a,
 author = {Alex J. Smola and Bernhard Sch\"{o}lkopf},
 title = {Sparse Greedy Matrix Approximation for Machine Learning},
 booktitle = {Proceedings of the 17th Annual International Conference on Machine Learning},
 pages = {911--918},
 year = {2000}
}

@Article{AJS98a,
 author = {Alex J. Smola and Bernhard Sch\"{o}lkopf},
 title = {A tutorial on support vector regression},
 journal = {Statistics and Computing},
 volume = {14},
 number = {3},
 year = {2004},
 issn = {0960-3174},
 pages = {199--222},
 doi = {http://dx.doi.org/10.1023/B:STCO.0000035301.49549.88},
 publisher = {Kluwer Academic Publishers},
 }


@Article{AJS98b,
  author = 	 {A.J. Smola and N. Murata and B. Sch\"{o}lkopf and K.-R.
M{\"u}ller},
  title = 	 {Asymptotically Optimal Choice of epsilon-Loss for Support
Vector Machines},
  year = 	 {1998},
 booktitle = {Proceedings of the International Conference on Artificial Neural Networks},
 pages = {105--110},
 publisher = {Springer-Verlag}
}

@InProceedings{   SmoSch00,
  author        = {A.J. Smola and B. Sch\"olkopf},
  title         = {Sparse Greedy Matrix Approximation for Machine Learning},
  booktitle     = {International Conference on Machine Learning},
  year          = {2000},
}

@incollection{AJS03a,
  title={Kernels and regularization on graphs},
  author={Smola, Alexander J and Kondor, Risi},
  booktitle={Learning theory and kernel machines},
  pages={144--158},
  year={2003},
  publisher={Springer}
}

@incollection{AS07a,
 title = {Bundle Methods for Machine Learning},
 author = {Alex J. Smola and S. V. N. Vishwanathan and Quoc Le},
 booktitle = {Advances in Neural Information Processing Systems 20},
 editor = {J.C. Platt and D. Koller and Y. Singer and S. Roweis},
 publisher = {MIT Press},
 address = {Cambridge, MA},
 pages = {},
 year = {2008}
}

@inproceedings{AS07a-short,
 title = {Bundle Methods for Machine Learning},
 author = {Alex J. Smola and S V N Vishwanathan and Quoc Le},
 booktitle = {{NIPS}},
 year = {2008}
}


@InProceedings{AS10a,
  title = 	 {An Architecture for Parallel Topic Models},
 author = {Smola, Alexander and Narayanamurthy, Shravan},
  booktitle = {Proceedings of the VLDB Endowment},
 volume = {3},
 number = {1-2},
 year = {2010},
 pages = {703--710}
}

@book{MS98a,
 author = {M. Snir and S. Otto},
 title = {{MPI}-the complete reference: the {MPI} core},
 year = {1998},
 publisher = {MIT Press},
 address = {Cambridge, MA, USA},
 }

@INPROCEEDINGS{CGMS06a,
  AUTHOR = {Cees G.M. Snoek and Marcel Worring and Jan C. van Gemert and Jan-Mark Geusebroek and Arnold W.M. Smeulders},
  TITLE = {The Challenge Problem for Automated Detection of 101 Semantic Concepts in Multimedia},
  BOOKTITLE = {Proceedings of the {ACM} International Conference on Multimedia},
  YEAR = {2006},
  ADDRESS = {Santa Barbara, USA}
}

@incollection{JS12a,
	title = {Practical {B}ayesian Optimization of Machine Learning Algorithms},
	author = {Snoek, Jasper and Larochelle, Hugo and Adams, Ryan P},
	booktitle = {Advances in Neural Information Processing Systems 25 (NIPS)},
	pages = {2951--2959},
	year = {2012},
        doi = {10.5555/2999325.2999464}
}

@incollection{JS12a-short,
	title = {Practical {B}ayesian Optimization of Machine Learning Algorithms},
	author = {J. Snoek and H. Larochelle and Adams, R. P.},
	booktitle = {NIPS},
	year = {2012}
}


@article{JS93,
author      = {J. Soares and J. J\'udice and F. Facchinei},
title       = {An active set {N}ewton's method for large-scale 
               nonlinear programs with box constraints},
journal     = {SIAM J. Optim.},
pages       = {158--186},
volume      = {8},
year        = {1998}
}



@InProceedings{TS06a,
  author = 	 {Tim Sohn and Alex Varshavsky and Anthony LaMarca and Mike Y. Chen and Tanzeem Choudhury and Ian Smith and Sunny Consolvo and William Griswold},
  title = 	 {Mobility Detection Using Everyday {GSM} Traces },
  OPTcrossref =  {},
  OPTkey = 	 {},
  booktitle = {Proceedings of the 8th International Conference on Ubiquitous Computing},
  OPTpages = 	 {},
  year =	 {2006},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTaddress = 	 {},
  OPTmonth = 	 {},
  OPTorganization = {},
  OPTpublisher = {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@article{PS02,
author      = {P. Sollich},
journal     = {Machine learning},
pages       = {21--52},
title       = {Bayesian methods for Support Vector Machines: Evidence and
predictive class probabilities},
volume      = {46},
year        = {2002}
}

@inproceedings{YS08a,
  author        = "Yangqiu Song and Wen-Yen Chen and Hongjie Bai and Chih-Jen Lin and Edward Y. Chang",
  title         = "Parallel Spectral Clustering",
  booktitle     = "European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML/PKDD)",
  url = {http://www.csie.ntu.edu.tw/~cjlin/papers/ecml08.pdf},
  year          = "2008"
}


@article{SS07a,
  title={The need for open source software in machine learning},
  author={Sonnenburg, S. and Braun, M.L. and Ong, C.S. and Bengio, S. and Bottou, L. and Holmes, G. and {LeCun}, Y. and M\"{u}ller, K.R. and Pereira, F. and Rasmussen, C.E. and others},
  journal={Journal of Machine Learning Research},
  volume={8},
  pages={2443--2466},
  year={2007}
}

@inproceedings{SS10a,
   author    = {Soeren Sonnenburg and Vojtech Franc},
   title     = {{COFFIN} : A Computational Framework for Linear {SVM}s},
   booktitle = {Proceedings of the Twenty Seventh International Conference 
on Machine Learning (ICML)},
   year      = {2010},
   pages     = {999--1006}
}

@ONLINE{SONY13a,
        author={Device Specifications},
	title = {Sony Smartwatch 2-Battery},
        howpublished = {\url{http://www.devicespecifications.com/en/model-battery/518829ce}}
}


@article{DCS97,
author      = {Danny C. Sorensen},
journal     = {SIAM J. Optim.},
pages       = {141--161},
title       = {Minimization of a large scale quadratic function 
               subject to a spherical constraint},
volume      = {7},
year        = {1997}
}

@misc{HJS24a,
  author = {Harold J. Spaeth and Lee Epstein and Andrew D. Martin and Jeffrey A. Segal and Theodore J. Ruger and Sara C. Benesh},
  title = {2024 Supreme Court Database, Version 2024 Release 01},
  year = {2024},
  url = {http://supremecourtdatabase.org}
}

@TechReport{PS98a,
  author = 	 {Peter Spellucci},
  title = 	 {{DONLP2} short users guide},
  institution =  {Technical University Darmstadt},
  year = 	 {1998},
  address =	 {Darmstadt, Germany}
}


@INPROCEEDINGS{NS05a,
    author = {Nathan Srebro and Jason D. M. Rennie and Tommi S. Jaakola},
    title = {Maximum-Margin Matrix Factorization},
    booktitle = {Advances in Neural Information Processing Systems},
    year = {2005},
    pages = {1329--1336},
}

@inproceedings{NS03a,
  title={Weighted low-rank approximations},
  author={Srebro, Nathan and Jaakkola, Tommi},
  booktitle={Proceedings of the 20th International Conference on Machine Learning (ICML)},
  pages={720--727},
  year={2003}
}

@inproceedings{VS12a,
 author = {Srinivasan, Vijay and Phan, Thomas},
 title = {An accurate two-tier classifier for efficient duty-cycling of smartphone activity recognition systems},
 booktitle = {Proceedings of the Third International Workshop on Sensing Applications on Mobile Phones (PhoneSense)},
 year = {2012},
 pages = {11:1--11:5}
}

@article{NS14a,
title={Dropout: a simple way to prevent neural networks from overfitting},
author={Srivastava, Nitish and Hinton, Geoffrey and Krizhevsky, Alex and Sutskever, Ilya and Salakhutdinov, Ruslan},
journal={The Journal of Machine Learning Research},
volume={15},
number={1},
pages={1929--1958},
year={2014}
}

@article{NS14a-short,
title={Dropout: a simple way to prevent neural networks from overfitting},
author={Srivastava, Nitish and Hinton, Geoffrey and Krizhevsky, Alex and Sutskever, Ilya and Salakhutdinov, Ruslan},
journal={JMLR},
year={2014}
}

@inproceedings{HS10a,
 author = {Steck, Harald},
 title = {Training and Testing of Recommender Systems on Data Missing Not at Random},
 booktitle = {Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)},
 year = {2010},
 pages = {713--722}
}

@inproceedings{HS10a-short,
 author = {Steck, Harald},
 title = {Training and Testing of Recommender Systems on Data Missing Not at Random},
 booktitle = {KDD},
 year = {2010}
}

@inproceedings{HS11a,
 author = {Steck, Harald},
 title = {Item Popularity and Recommendation Accuracy},
 booktitle = {Proceedings of the Fifth ACM Conference on Recommender Systems},
 year = {2011},
 pages = {125--132}
}

@inproceedings{HS11a-short,
 author = {Steck, Harald},
 title = {Item Popularity and Recommendation Accuracy},
 booktitle = {RecSys},
 year = {2011}
}


@inproceedings{HS13a,
 author = {Steck, Harald},
 title = {Evaluation of Recommendations: Rating-prediction and Ranking},
 booktitle = {Proceedings of the 7th ACM Conference on Recommender Systems},
 year = {2013},
 pages = {213--220}
}

@inproceedings{HS13a-short,
 author = {Steck, Harald},
 title = {Evaluation of Recommendations: Rating-prediction and Ranking},
 booktitle = {RecSys},
 year = {2013}
}

@article{TS83a,
author      = {Trond Steihaug},
journal     = {SIAM Journal on Numerical Analysis},
pages       = {626--637},
title       = {The conjugate gradient method and trust regions in large scale optimization},
volume      = {20},
year        = {1983}
}

@article{TS83a-short,
author      = {Trond Steihaug},
journal     = {SIAM J. Numer. Anal.},
pages       = {626--637},
title       = {The conjugate gradient method and trust regions in large scale optimization},
volume      = {20},
year        = {1983}
}


@Article{IS02a,
  author = 	 {Ingo Steinwart},
  title = 	 {Support vector machines are universally consistent},
  journal = 	 {Journal of Complexity},
  year = 	 {2002},
  volume =	 {18},
  pages =	 {768--791}
}


@Article{IS03a,
  author = 	 {Ingo Steinwart},
  title = 	 {On the optimal parameter choice for $\nu$-support vector machines},
  journal = 	 {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = 	 {2003},
  note =	 {To appear}
}



@Article{IS03b,
 author = {Steinwart, Ingo},
 title = {Sparseness of support vector machines},
  journal = 	 {Journal of Machine Learning Research},
 volume = {4},
 year = {2003},
 pages = {1071--1105}
}

@article{IS11a,
  title={Training {SVM}s without offset},
  author={Steinwart, Ingo and Hush, Don and Scovel, Clint},
  journal={Journal of Machine Learning Research},
  volume={12},
  pages={141--202},
  year={2011}
}

@article{IS11a-short,
  title={Training {SVM}s without offset},
  author={Steinwart, Ingo and Hush, Don and Scovel, Clint},
  journal={JMLR},
  volume={12},
  pages={141--202},
  year={2011}
}

@inproceedings{LS11a,
author = {Stenneth, Leon and Wolfson, Ouri and Yu, Philip S. and Xu, Bo},  
title = {Transportation mode detection using mobile phones and {GIS} information},  
booktitle = {Proceedings of the 19th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems},  
series = {GIS '11},  
year = {2011}
} 

@Misc{AS17a,
author = {Andreas Sterbenz},
title = {Using {G}oogle Cloud Machine Learning to predict clicks at scale},
year = {2017},
howpublished = {\url{https://cloud.google.com/blog/big-data/2017/02/using-google-cloud-machine-learning-to-predict-clicks-at-scale}}
}


@inproceedings{DS09b,
 author = {Stern, David H. and Herbrich, Ralf and Graepel, Thore},
 title = {Matchbox: Large Scale Online Bayesian Recommendations},
 booktitle = {Proceedings of the 18th International Conference on World Wide Web (WWW)},
 year = {2009},
 pages = {111--120}
} 


@book{DES94,
author      = {D. E. Stewart and Z. Leyk},
title       = {Meschach : Matrix Computations in C},
publisher   = {Australian National University},
year        = {1994},
series      = {Proceedings of the Center of Mathematics and Its Application},
volume      = {32},
}

@article{MS01a,
  title={{The Interaction of Knowledge Sources in Word Sense Disambiguation}},
  author={Stevenson, M. and Wilks, Y.},
  journal={Computational Linguistics},
  volume={27},
  number={3},
  pages={321--349},
  year={2001},
  publisher={MIT Press}
}

@Article{RAS85a,
  author = 	 {Robert A. Stine},
  title = 	 {Bootstrap prediction intervals for regression},
  journal = 	 {Journal of the American Statistical Association},
  year = 	 {1985},
  volume =	 {80},
  number =	 {392},
  pages =	 {1026--1029},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@TechReport{MOS96a,
  author = 	 "M. O. Stitson and J. A. E. Weston and 
		  A. Gammerman and V. Vovk and V. Vapnik",
  title = 	 "Theory of support vector machines",
  institution =  "Department of Computer Science, University of London",
  year = 	 "1996",
  number =	 "CSD-TR-96-17",
  address =	 "Egham, UK"
}

@InProceedings{MOS99a,
  author	= {M. O. Stitson and A. Gammerman and V. Vapnik and V. Vovk and
		  C. Watkins and J. Weston},
  title		= {Support Vector Regression with {ANOVA} Decomposition
		  Kernels},
  year		= {1999},
  pages		= {285--292},
  crossref =	 "BS98a"
}

@article{MS74a,
  title = {Cross-Validatory Choice and Assessment of Statistical Predictions},
  author={Stone, Mervyn},
  journal={Journal of the Royal Statistical Society: Series B (Methodological)},
  volume={36},
  number={2},
  pages={111--147},
  year={1974}
}

@inproceedings{AS00a,
  author = {Strehl, Alexander and Ghosh, Joydeep and Mooney, Raymond},
  booktitle = {Proceedings of the AAAI Workshop on AI for Web Search},
  pages = {58--64},
  title = {Impact of Similarity Measures on Web-page Clustering},
  year = {2000}
}

@inproceedings{AS00a-short,
  author = {Strehl, Alexander and Ghosh, Joydeep and Mooney, Raymond},
  booktitle = {AAAI Workshop on AI for Web Search},
  title = {Impact of Similarity Measures on Web-page Clustering},
  year = {2000}
}

@inproceedings{AS10b,
 author = {Strehl, Alexander L. and Langford, John and Li, Lihong and Kakade, Sham M.},
 title = {Learning from Logged Implicit Exploration Data},
 booktitle = {Proceedings of the 23rd International Conference on Neural Information Processing Systems (NIPS)},
 year = {2010},
 pages = {2217--2225}
} 

@techreport {JFS95a,
         author  = "J.F. Sturm and S. Zhang",
         title   = "Symmetric primal-dual path following algorithms for
   semidefinite programming",
         institution = "Erasmus University Rotterdam",
         number = "9554/A",
         year    = "1995",
         address  = "The Netherlands"
     }

@conference{PS96a,
title={A Factorization Based Algorithm for Multi-image Projective Structure and Motion},
booktitle={Fourth European Conference on Computer Vision},
author={Peter Sturm and Bill Triggs},
pages={709--720},
year={1996},
}

@article{AS04a,
  title={Blocking Reduction Strategies in Hierarchical Text Classification},
  author={Sun, Aixin and Lim, Ee-Peng and Ng, Wee-Keong and Srivastava, Jaideep},
  journal={IEEE Transactions on Knowledge and Data Engineering},
  volume={16},
  number={10},
  pages={1305--1308},
  year={2004}
}

@article{AS09a,
  title={On strategies for imbalanced text classification using SVM: A comparative study},
  author={Sun, Aixin and Lim, Ee-Peng and Liu, Ying},
  journal={Decision Support Systems},
  issn={0167--9236},
  volume={48},
  number={1},
  pages={191--201},
  year={2009}
}

@article{DHS05a,
  title={A Novel Method for Chinese Spam detection based on One-Class Support Vector Machine},
  author={Sun, Donghong and Tran, Quang-Anh and Duan, Haixin and Zhang, Guodong},
  journal={Journal of Information and Computational Science},
  volume={2},
  number={1},
  pages={109--114},
  year={2005}
}

@article{RS16a,
author = {Sun, Ruoyu and Ye, Yinyu},
year = {2019},
journal={Mathematical Programming},
title = {Worst-case Complexity of Cyclic Coordinate Descent: {$O(n^2)$} Gap with Randomized Version}
}

@article{RS16a-short,
author = {Sun, Ruoyu and Ye, Yinyu},
year = {2019},
journal={Math. Program.},
title = {Worst-case Complexity of Cyclic Coordinate Descent: {$O(n^2)$} Gap with Randomized Version}
}

@InProceedings{YS21a,
author="Sun, Yuchen
and Wan, Liangtian
and Sun, Lu
and Wang, Xianpeng",
title="Z-NetMF: A Biased Embedding Method Based on Matrix Factorization",
booktitle="Proceedings of the 9th International Conference on Communications, Signal Processing, and Systems",
year="2021",
pages="1669--1676"
}

@inproceedings{IS13a,
    Author = {Ilya Sutskever and James Martens and George Dahl and Geoffrey Hinton},
    Booktitle = {Proceedings of the 30th International Conference on Machine Learning (ICML)},
    Title = {On the importance of initialization and momentum in deep learning},
    Year = {2013},
    Pages = {1139--1147}
} 


@InCollection{CS06a,
  author = 	 {Charles Sutton and Andrew McCallum},
  title = 	 {An Introduction to Conditional Random Fields for Relational Learning
},
  booktitle = 	 {Introduction to Statistical Relational Learning},
  OPTcrossref =  {},
  OPTkey = 	 {},
  OPTpages = 	 {},
  publisher =	 {MIT Press},
  year =	 {2006},
  editor =	 {Lise Getoor and Ben Taskar},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTtype = 	 {},
  OPTchapter = 	 {},
  OPTaddress = 	 {},
  OPTedition = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@Article{JAKS99a,
  author = {J.A.K. Suykens and J. Vandewalle},
  title = "Least Square Support Vector Machine Classifiers",
  year = {1999},
  journal={Neural Processing Letters},
  volume={9},
  number={3},
  pages={293--300}
}

@InProceedings{JAKS99b,
  author = {J.A.K. Suykens and J. Vandewalle},
  title =    "Multiclass {LS-SVM}s: Moderated Outputs and Coding-Decoding Schemes",
  year =     "1999",
  booktitle =    "Proceedings of IJCNN",
  address =  "Washington D.C." 
}



@Article{VS03a,
  author = 	 {Vladimir Sventnik and Andy Liaw and Christopher Tong and J. Christopher Culberson and Robert P. Sheridan and Bradley P. Feuston},
  title = 	 {Random forest: a tool for  classification and regression in compound  classification and {QSAR} modeling},
  journal = 	 {Journal of Chemical Information and Computer Science},
  year = 	 {2003},
  volume =	 {43},
  number =	 {6},
  pages =	 {1947--1958},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@Article{VS04a,
  author =     {Vladimir Sventnik and Andy Liaw and Christopher Tong},
  title =      {Variable Selection in Random Forest with Application to Quantitative Structure-Activity Relationship},
  year =       {2004},
}


@InProceedings{VS04b,
 author    = {Vladimir Svetnik and
             Andy Liaw and
             Christopher Tong and
             Ting Wang},
  title = 	 {Application
of {B}reiman's random forest to modeling structure-activity relationships
of pharmaceutical molecules},
  booktitle = 	 {Proceedings of the 5th International Workshopon Multiple Classifier Systems},
  OPTcrossref =  {},
  OPTkey = 	 {},
  pages =	 {334--343},
  year =	 {2004},
  editor =	 {F. Roli and J. Kittler and T. Windeatt},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  series =	 {Lecture Notes in Computer Science vol. 3077.},
  OPTaddress = 	 {Berlin},
  OPTmonth = 	 {},
  OPTorganization = {},
  publisher =	 {Springer},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@article{AS15a,
title={Batch learning from logged bandit feedback through counterfactual risk minimization},
author={Swaminathan, Adith and Joachims, Thorsten},
journal={Journal of Machine Learning Research},
volume={16},
number={1},
pages={1731--1755},
year={2015}
}

@article{AS15a-short,
title={Batch learning from logged bandit feedback through counterfactual risk minimization},
author={Swaminathan, Adith and Joachims, Thorsten},
journal={JMLR},
volume={16},
pages={1731--1755},
year={2015}
}

@inproceedings{AS15b,
 author = {Swaminathan, Adith and Joachims, Thorsten},
 title = {The Self-normalized Estimator for Counterfactual Learning},
 booktitle = {Proceedings of the 28th International Conference on Neural Information Processing Systems (NIPS)},
 year = {2015},
 pages = {3231--3239}
} 

@article{AS16a,
author = {Swaminathan, Adith and Krishnamurthy, Akshay and Agarwal, Alekh and Dud\'{\i}k, Miroslav and Langford, John and Jose, Damien and Zitouni, Imed},
title = {Off-Policy Evaluation for Slate Recommendation},
year = {2017},
booktitle = {Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS)},
pages = {3635–3645}
}

@incollection{KS13a,
title = {Multi-Task Bayesian Optimization},
author = {Swersky, Kevin and Snoek, Jasper and Adams, Ryan P},
booktitle = {Advances in Neural Information Processing Systems 26},
editor = {C. J. C. Burges and L. Bottou and M. Welling and Z. Ghahramani and K. Q. Weinberger},
pages = {2004--2012},
year = {2013}
}

@InProceedings{NAS99a,
  author = 	 {Syed, N. A. and Liu, H. and  Sung, K. K.},
  title = 	 {Incremental learning with
support vector machines},
  booktitle = 	 {Workshop on {S}upport {V}ector {M}achines, {IJCAI}99},
  year =	 {1999}
}


@article{sz:fa,
author      = {H. Szu and R. Hartley},
journal     = {Physics Letters A},
pages       = {157--162},
title       = {Fast simulated annealing},
volume      = {122},
year        = {1987}
}

@article{PS19a,
  author  = {Piotr Szyma{{\'n}}ski and Tomasz Kajdanowicz},
  title   = {Scikit-multilearn: A Python library for Multi-Label Classification},
  journal = {Journal of Machine Learning Research},
  year    = {2019},
  volume  = {20},
  number  = {6},
  pages   = {1-22}
}

@InProceedings{RS21a,
  title = 	 {Top-k eXtreme Contextual Bandits with Arm Hierarchy},
  author =       {Sen, Rajat and Rakhlin, Alexander and Ying, Lexing and Kidambi, Rahul and Foster, Dean and Hill, Daniel N and Dhillon, Inderjit S.},
  booktitle = 	 {Proceedings of the 38th International Conference on Machine Learning (ICML)},
  pages = 	 {9422--9433},
  year = 	 {2021}
}

@InProceedings{SS17a,
  title = 	 {Gradient Boosted Decision Trees for High Dimensional Sparse Output},
  author =       {Si Si and Huan Zhang and S. Sathiya Keerthi and Dhruv Mahajan and Inderjit S. Dhillon and Cho-Jui Hsieh},
  booktitle = 	 {Proceedings of the 34th International Conference on Machine Learning (ICML)},
  pages = 	 {3182--3190},
  year = 	 {2017}
}

@techreport{BC09,
  author =	 {Andreas T\"oscher and Michael Jahrer},
  title =	 {The {BigChaos} Solution to the {Netflix} Grand
                  Prize},
  year =	 {2009},
}

@INPROCEEDINGS{APT15a, 
 author={Anh-Phuong Ta}, 
 booktitle = {Proceedings of the IEEE International Conference on Big Data},
 title={Factorization machines with follow-the-regularized-leader for {CTR} prediction in display advertising}, 
 year={2015}, 
}

@InCollection{JT81a,
  author =       {Jean M. Tague},
  editor =       {Karen Sparck Jones},
  title =        {Information Retrieval Experiment},
  publisher =    {Butterworths},
  year =         {1981},
  address =      {London},
  pages =        {59--102},
  booktitle = 	 {The pragmatics of information retrieval experimentation},
  OPTcrossref =  {},
  OPTkey = 	 {},
  OPTyear = 	 {},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTtype = 	 {},
  chapter =	 {5},
  OPTedition = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}


@ARTICLE{FT12a,
  author={Tai, Farbound and Lin, Hsuan-Tien},
  journal={Neural Computation}, 
  title={Multilabel Classification with Principal Label Space Transformation}, 
  year={2012},
  volume={24},
  pages={2508--2542}
}

@Article{EDT91a,
  author = 	 {E. D. Taillard},
  title = 	 {Robust tabu search for the quadratic assignment problem},
  journal = 	 {Parallel Computing},
  year = 	 {1991},
  volume =	 {17},
  pages =	 {443--455}
}

@article{GT09a,
author = {Tak\'{a}cs, G\'{a}bor and Pil\'{a}szy, Istv\'{a}n and N{\'e}meth, Botty\'{a}n and Tikk, Domonkos},
title = {Scalable Collaborative Filtering Approaches for Large Recommender Systems},
journal = {Journal of Machine Learning Research},
volume = {10},
year = {2009},
pages = {623--656},
} 

@article{GT09a-short,
author = {Tak\'{a}cs, G\'{a}bor and Pil\'{a}szy, Istv\'{a}n and N{\'e}meth, Botty\'{a}n and Tikk, Domonkos},
title = {Scalable Collaborative Filtering Approaches for Large Recommender Systems},
journal = {JMLR},
volume = {10},
year = {2009},
pages = {623--656},
} 
@misc{RT13a,
title={Inexact coordinate descent: complexity and preconditioning},
author={Tappenden, Rachael and Richt{\'a}rik, Peter and Gondzio, Jacek},
note={arXiv preprint arXiv:1304.5530},
year={2013}
}


@article{DMT02a,
  title={Uniform Object Generation for Optimizing One-class Classifiers},
  author={Tax, David M. J. and Duin, Robert P. W.},
  journal={Journal of Machine Learning Research},
  volume={2},
  pages={155--173},
  year={2002}
}

@article{DMT04a,
  title={Support vector data description},
  author={Tax, David M. J. and Duin, Robert P. W.},
  journal={Machine Learning},
  volume={54},
  number={1},
  pages={45--66},
  year={2004},
  publisher={Springer}
}


@article{DMT04a-short,
  title={Support vector data description},
  author={Tax, David M. J. and Duin, Robert P. W.},
  journal={MLJ},
  volume={54},
  pages={45--66},
  year={2004}
}

@InProceedings{JT11a,
  author = 	 {Justin Talbot and Richard M. Yoo and Christos Kozyrakis},
  title = 	 {Phoenix++: Modular MapReduce for Shared-Memory Systems},
  OPTcrossref =  {},
  OPTkey = 	 {},
  booktitle =	 {Second International Workshop on MapReduce and its Applications},
  OPTpages = 	 {},
  year =	 {2011},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTaddress = 	 {},
  month =	 {June},
  OPTorganization = {},
  OPTpublisher = {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@inproceedings{MT13a,
 author = {Tak\'{a}\v{c}, Martin and Bijral, Avleen and Richt\'{a}rik, Peter and Srebro, Nathan},
 title = {Mini-batch Primal and Dual Methods for SVMs},
 booktitle = {Proceedings of the 30th International Conference on International Conference on Machine Learning (ICML)},
 year = {2013}
}

@inproceedings{MT13a-short,
 author = {Tak\'{a}\v{c}, Martin and Bijral, Avleen and Richt\'{a}rik, Peter and Srebro, Nathan},
 title = {Mini-batch Primal and Dual Methods for SVMs},
 booktitle = {ICML},
 year = {2013}
}

@misc{MT15a,
  title={Distributed Mini-Batch {SDCA}},
  author={Martin Tak\'{a}\v{c} and Peter Richt\'{a}rik and Nathan Srebro},
  note={arXiv preprint arXiv:1507.08322},
  year={2015}
}

@misc{MT15a-short,
  title={Distributed Mini-Batch {SDCA}},
  author={Martin Tak\'{a}\v{c} and Peter Richt\'{a}rik and Nathan Srebro},
  note={arXiv},
  year={2015}
}


@Article{NT05a,
  author = 	 {Norikazu Takahashi and Tetsuo Nishi},
  title = 	 {Rigorous proof of termination of {SMO} algorithm for support vector machines},
  journal = 	 {IEEE Transactions on Neural Networks},
  year = 	 {2005},
  OPTkey = 	 {},
  volume =	 {16},
  number =	 {3},
  pages =	 {774--776},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}



@Article{NT06a,
  author = 	 {Takahashi, N. and  Nishi, T.},
  title = 	 {Global Convergence of Decomposition Learning Methods for Support Vector Machines},
  journal = 	 {IEEE Transactions on Neural Networks},
  year = 	 {2006},
  OPTkey = 	 {},
  volume =	 {17},
  number =	 {6},
  pages =	 {1362--1369},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@Article{YT02a,
  author = 	 {Y. Tan and Y. Xia and J. Wang},
  title = 	 {Neural netowrk realization of support
vector methods for pattern recognition},
  journal = 	 {IEEE Transactions on Neural Networks},
  year = 	 {2002},
  note={To appear}
}

@inproceedings{JT15a,
  title={Line: Large-scale information network embedding},
  author={Tang, Jian and Qu, Meng and Wang, Mingzhe and Zhang, Ming and Yan, Jun and Mei, Qiaozhu},
  booktitle={Proceedings of the 24th international Conference on World Wide Web (WWW)},
  pages={1067--1077},
  year={2015}
}

@inproceedings{LT09a,
  title={Relational learning via latent social dimensions},
  author={Tang, Lei and Liu, Huan},
  booktitle={Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining (KDD)},
  pages={817--826},
  year={2009}
}

@inproceedings{LT09b,
  title={Scalable learning of collective behavior based on sparse social dimensions},
  author={Tang, Lei and Liu, Huan},
  booktitle={Proceedings of the 18th ACM conference on Information and Knowledge Management (CIKM)},
  pages={1107--1116},
  year={2009}
}

@inproceedings{LT09c,
  title={Large scale multi-label classification via metalabeler},
  author={Tang, Lei and Rajan, Suju and Narayanan, Vijay K.},
  booktitle={Proceedings of the 18th International Conference on World Wide Web (WWW)},
  pages={211--220},
  year={2009}
}

@inproceedings{LT10a,
author = {Tang, Lei and Wang, Xufei and Liu, Huan and Wang, Lei},
title = {A Multi-Resolution Approach to Learning with Overlapping Communities},
year = {2010},
booktitle = {Proceedings of the First Workshop on Social Media Analytics},
pages = {14--22}
}

@article{LT11a,
  title={Leveraging social media networks for classification},
  author={Tang, Lei and Liu, Huan},
  journal={Data Mining and Knowledge Discovery},
  volume={23},
  pages={447--478},
  year={2011}
}

@article{LT12a,
  title={Scalable learning of collective behavior},
  author={Tang, Lei and Wang, Xufei and Liu, Huan},
  journal={IEEE Transactions on Knowledge and Data Engineering},
  volume={24},
  pages={1080--1091},
  year={2012}
}


@incollection{BT04a,
  author = {Ben Taskar and  Carlos Guestrin and  Daphne Koller},
  title = {Max-Margin Markov Networks},
  booktitle = {Advances in Neural Information Processing Systems 16},
  publisher = {MIT Press},
  address = {Cambridge, MA},
  year = {2004}
}

@inproceedings{GT16a,
  author={Taylor, Gavin and Burmeister, Ryan and Xu, Zheng and Singh,
Bharat and Patel, Ankit and Goldstein, Tom},
  title={Training neural networks without gradients: A scalable {ADMM}
approach},
  booktitle = {Proceedings of The Thirty Third International Conference on
Machine Learning},
  pages = {2722--2731},
  year = {2016}
}

@inproceedings{CT12a,
  author    = {Christina Teflioudi and
               Faraz Makari and
               Rainer Gemulla},
  title     = {Distributed Matrix Completion},
  booktitle = {ICDM},
  year      = {2012},
  pages     = {655-664},
  ee        = {http://doi.ieeecomputersociety.org/10.1109/ICDM.2012.120},
  bibsource = {DBLP, http://dblp.uni-trier.de}
}

@article{FT20a,
  title={Explainable Prediction of Medical Codes With Knowledge Graphs},
  author={Teng, Fei and Yang, Wei and Chen, Li and Huang, LuFei and Xu, Qiang},
  journal={Frontiers in Bioengineering and Biotechnology},
  volume={8},
  pages={867},
  year={2020},
  doi={10.3389/fbioe.2020.00867}
}

@inproceedings{CHT07a,
    author = {Choon Hui Teo and Alex Smola and S. V. N. Vishwanathan
and Quoc Viet Le},
    title = {A scalable modular convex solver for regularized risk
minimization},
    booktitle = {Proceedings of the 13th ACM SIGKDD
international conference on Knowledge discovery and data mining},
    year = {2007},
    isbn = {978-1-59593-609-7},
    pages = {727--736},
    location = {San Jose, California, USA},
    doi = {http://doi.acm.org/10.1145/1281192.1281270},
    publisher = {ACM},
    address = {New York, NY, USA},
}

@inproceedings{CHT07a-short,
    author = {Choon Hui Teo and Alex Smola and S. V. N. Vishwanathan
and Quoc Viet Le},
    title = {A scalable modular convex solver for regularized risk
minimization},
    booktitle = {ACM KDD},
    year = {2007}
}

@Article{CHT09a,
  author = {Choon Hui Teo and S.V.N. Vishwanathan and Alex Smola and
Quoc V. Le},
  title = {Bundle Methods for Regularized Risk Minimization},
  journal = 	 {Journal of Machine Learning Research},
  volume={11},
  pages={311--365},
  year={2010}
}

@article{RT05a,
  title={Optimization of collective communication operations in {MPICH}},
  author={Thakur, Rajeev and Rabenseifner, Rolf and Gropp, William},
  journal={International Journal of High Performance Computing Applications},
  volume={19},
  number={1},
  pages={49--66},
  year={2005}
}


@InProceedings{CT13a,
    author =   {Chris Thornton and Frank Hutter and Holger Hoos and Kevin Leyton-Brown},
    title =  {Auto-{WEKA}: Combined Selection and Hyperparameter Optimization of Classification Algorithms},
  booktitle =	 {Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)},
    year = 2013,
    pages = {847-855}
}

@article{LLT27a,
author      = {Louis L. Thurstone},
journal     = {Psychological Reviews},
pages       = {273--286},
title       = {A law of comparative judgement},
volume      = {34},
year        = {1927}
}

@inproceedings{AT10a,
  title={Hive-a petabyte scale data warehouse using hadoop},
  author={Ashish Thusoo and Joydeep Sen Sarma and Namit Jain and Zheng Shao and Prasad Chakka and Ning Zhang and Suresh Antony and Hao Liu
and Raghotham Murthy},
  booktitle={Proceedings of 26th IEEE International Conference on Data Engineering (ICDE)},
  pages={996--1005},
  year={2010}
}

@Article{RT96a,
  author = {Robert Tibshirani},
  title = {Regression Shrinkage and Selection via the
Lasso},
  journal = {Journal of the Royal Statistical
Society Series B},
  year = {1996},
  pages = {267--288},
  volume = {58}
}
%   url = {http://www-stat.stanford.edu/~tibs/lasso/lasso.pdf},

@article{RT10a,
  author = {Tibshirani, Robert and Bien, Jacob and Friedman, Jerome
and Hastie, Trevor and Simon, Noah and Taylor, Jonatha and Tibshirani,
Ryan J.},
  title = {Strong Rules for Discarding Predictors in Lasso-type Problems},
  journal = {Journal of Royal Statistical Society: Series B},
  year = {2012},
  volume={74}, 
  pages={245--266}
}

@article{RT10a-short,
  author = {R. Tibshirani and J. Bien and J. Friedman and T. Hastie and 
	  N. Simon and J. Taylor and R. J. Tibshirani},
  title = {Strong Rules for Discarding Predictors in Lasso-type Problems},
  journal = {JRSSB},
  year = {2012},
  volume={74}, 
  pages={245--266}
}

@article{ti:ac,
author      = {Luke Tierney and Joseph B. Kadane},
journal     = {Journal of the American Statistical Association},
pages       = {82--86},
title       = {Accurate approximations for posterior moments and
               marginal densities},
volume      = {81},
year        = {1986}
}


@article{ANT63a,
        author   = {A.N. Tikhonov},
        format   = {print},
        journal  = {Sov. Math. Dokl.},
        keywords = {no keywords},
        pages    = {1035--1038},
        refdb_id = {http://solarphysics.livingreviews.org/refdb/record/9432},
        title    = {Solution of Incorrectly Formulated Problems and the Regularization Method},
        volume   = {4},
        year     = {1963}
}

@article{WFT67a,
  title={Direct solutions of sparse network equations by optimally ordered triangular factorization},
  author={Tinney, William F and Walker, John W},
  journal={Proceedings of the IEEE},
  volume={55},
  pages={1801--1809},
  year={1967}
}

@article{WFT67a-short,
  title={Direct solutions of sparse network equations by optimally ordered triangular factorization},
  author={Tinney, William F and Walker, John W},
  journal={PIEEE},
  volume={55},
  pages={1801--1809},
  year={1967}
}


@Misc{MJT97a,
  author = 	 {M. J. Todd},
  title =	 {Properties of search directions for semidefinite programming},
  note =	 {Talk given at the 16th Mathematical Programming Symposium, Laussane},
  month =        {August 24-29},
  year =         {1997}
}



@TechReport{MJT97b,
  author = 	 {M. J. Todd},
  title = 	 {On search directions in interior-point methods                        
     for semidefinite programming},
  institution =  {School of Operations Research and
     Industrial Engineering, Cornell University},
  year = 	 {1997},
  type =	 {Technical Report},
  number =	 {1205},
  address =	 {Ithaca, NY}
}

@techreport{MJT96a,
  author =	 {M.J. Todd and K.C. Toh and R.H. T\"ut\"unc\"u},
 title = "On the {N}esterov-{T}odd direction in semidefinite programming",
 year = "1996",
   number = "TR1154",
 institution = "School of OR and IE, Cornell University",
 address = "Ithaca, NY",
 }



@Manual{KCT96a,
  title = 	 {SDPT3 --- a {MATLAB} software package for semidefinite
   programming},
  author =	 {K.C. Toh and M.J. Todd and R.H. T\"ut\"unc\"u},
  year =	 {1996},
  month =	 {December},
  note =	 {Available at http://www.math.nus.sg/\~{ }mattohkc/index.html},
}

@article{PLT88,
author      = {Ph. L. Toint},
journal     = {IMA J. Numer. Anal.},
pages       = {231--252},
title       = {Global convergence of a class of trust region methods for 
nonconvex minimization in {H}ilbert space},
volume      = {8},
year        = {1988}
}

@article{AMT15a,
author={Tom{\'e}, Ana Maria and Schachtner, Reinhard and Vigneron, Vincent and Puntonet, Carlos Garcia and Lang, Elmar Wolfgang},
title={A logistic non-negative matrix factorization approach to binary data sets},
journal={Multidimensional Systems and Signal Processing},
volume={26},
number={1},
year={2015},
pages={125--143},
}


@article{RT09a,
  title={Dual augmented {L}agrangian method for efficient sparse reconstruction},
  author={Tomioka, Ryota. and Sugiyama, Masashi},
  journal={IEEE Signal Processing Letters},
  volume={16},
  number={12},
  pages={1067--1070},
  year={2009}
}




@Article{RT11a,
  author = 	 {Ryota Tomioka and Taiji Suzuki and Masashi Sugiyama},
  title = 	 {Super-Linear Convergence of Dual Augmented {L}agrangian Algorithm for Sparse Learning},
  journal =  {Journal of Machine Learning Research},
  volume =	 {12},
  pages =	 {1537--1586},
  year =	 {2011}
}

@Article{ST02a,
  author = 	 {Simon Tong and Daphne Koller},
  title = 	 {Support vector machine active learning with applications to text classification},
  journal = 	 {Journal of Machine Learning Research},
  year = 	 {2002},
  volume =	 {2},
  pages =	 {45--66}
}

@Misc{ST10a,
  OPTkey = 	 {},
  author =	 {Simon Tong},
  title =	 {Lessons learned developing a practical large scale machine learning system},
  howpublished = {Google Research Blog},
  OPTmonth = 	 {},
  year =	 {2010},
  note= {\url{http://googleresearch.blogspot.com/2010/04/lessons-learned-developing-practical.html}},
  OPTannote = 	 {}
}

@Article{VT97a,
  author = 	 {Virginia Torczon and Michael W. Trosset},
  title = 	 {From evolutionary operation to parallel direct
search: pattern search algorithms for numerical
optimization},
  journal = 	 {Computing Science and Statistics},
  year = 	 {1997},
  volume =	 {29},
  number =	 {1}
}

@article{VT09a,
 author = {Torvik, Vetle I. and Smalheiser, Neil R.},
 title = {Author name disambiguation in {MEDLINE}},
 journal = {ACM Transactions on Knowledge Discovery from Data},
 volume = {3},
 number = {3},
 year = {2009},
 pages = {11:1--11:29},
}

@ARTICLE{AT09,
  author = {Andreas T\"{o}scher and Michael Jahrer},
  title = {The {B}ig{C}haos Solution to the {N}etflix Grand Prize},
  year = {2009}
}

@InProceedings{KT00a,
  author =       {Kristina Toutanova and Christopher D. Manning},
  title =        {Enriching the Knowledge Sources Used in a Maximum Entropy Part-of-Speech Tagger},
  booktitle =    {Proceedings of the Joint SIGDAT Conference on Empirical Methods in Natural Language Processing and Very Large Corpora (EMNLP/VLC-2000)},
  year =         {2000},
  pages =        {63--70}
}

@misc{JT17a,
  author = {Jamie Townsend},
  title = {A new trick for calculating {J}acobian vector products},
  year = 2017,
  url = {https://j-towns.github.io/2017/06/12/A-new-trick.html}
}


@InProceedings{KT15a,
  author = 	 {Kenneth Tran and Saghar Hosseini and Lin Xiao
and Thomas Finley and Mikhail Bilenko},
  title = 	 {Scaling Up Stochastic Dual Coordinate Ascent},
  booktitle =	 {Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)},
  year =	 {2015},
  OPTcrossref =  {},
  OPTkey = 	 {},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTpages = 	 {},
  OPTmonth = 	 {},
  OPTaddress = 	 {},
  OPTorganization = {},
  OPTpublisher = {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@InProceedings{KT15a-short,
  author = 	 {Kenneth Tran and Saghar Hosseini and Lin Xiao
and Thomas Finley and Mikhail Bilenko},
  title = 	 {Scaling Up Stochastic Dual Coordinate Ascent},
  booktitle =	 {KDD},
  year =	 {2015}
}

@inproceedings{PT09b,
 author = {Treeratpituk, Pucktada and Giles, Clyde Lee},
 title = {Disambiguating authors in academic publications using random forests},
 booktitle = {Proceedings of the 9th ACM/IEEE-CS Joint Conference on Digital Libraries},
 year = {2009},
 pages = {39--48}
}

@article{OT01a,
title={Missing value estimation methods for DNA microarrays},
author={Olga Troyanskaya and Michael Cantor and Gavin Sherlock and Pat Brown and Trevor Hastie and Robert Tibshirani and David Botstein and Russ B. Altman},
journal={Bioinformatics},
volume={17},
number={6},
pages={520--525},
year={2001},
publisher={Oxford Univ Press}
}

@inproceedings{CHT14a,
 author = {Cheng-Hao Tsai and Chieh-Yen Lin and Chih-Jen Lin},
 title = {Incremental and decremental training for linear classification},
 booktitle = {Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining},
 year = {2014},
 url = {http://www.csie.ntu.edu.tw/~cjlin/papers/ws/inc-dec.pdf}
} 

@inproceedings{CHT14a-short,
 author = {Cheng-Hao Tsai and Chieh-Yen Lin and Chih-Jen Lin},
 title = {Incremental and decremental training for linear classification},
 booktitle = {KDD},
 year = {2014}
} 

@inproceedings{MHT10a,
   author    = {Ming-Hen Tsai and Chia-Hua Ho and Chih-Jen Lin},
   title     = {Active Learning Strategies Using {SVM}},
   booktitle = {Proceedings of IJCNN},
   year      = {2010},
   pages     = {}
}

@inproceedings{SCT19a,
  title={Leveraging hierarchical category knowledge for data-imbalanced multi-label diagnostic text understanding},
  author={Tsai, Shang-Chi and Chang, Ting-Yun and Chen, Yun-Nung},
  booktitle={Proceedings of the Tenth International Workshop on Health Text Mining and Information Analysis},
  pages={39--43},
  doi = "10.18653/v1/D19-6206",  
  year={2019}
}

@article{IWT05a,
  title={Core vector machines: Fast {SVM} training on very large data sets},
  author={Tsang, I.W. and Kwok, J.T. and Cheung, P.M.},
  journal={Journal of Machine Learning Research},
  volume={6},
  pages={363--392},
  year={2005}
}


@article{PT91a,
  title={Decomposition algorithm for convex differentiable minimization},
  author={Paul Tseng},
  journal={Journal of Optimization Theory and Applications},
  volume={70},
  number={1},
  pages={109--135},
  year={1991}
}


@TechReport{PT96a,
  author = 	 {Paul Tseng},
  title = 	 {Search direction and convergence analysis of some infeasible path-following methods for the monotone semi-definite LCP},
  institution =  {Department of Mathematics, University of Washington},
  year = 	 {1996},
  address =	 {Seattle, Washington}
}


@article{PT07a,
title={A coordinate gradient descent method for nonsmooth separable minimization},
author={Tseng, Paul and Yun, Sangwoon},
journal={Mathematical Programming},
volume={117},
pages={387--423},
year={2009}
}

@article{PT07a-short,
title={A coordinate gradient descent method for nonsmooth separable minimization},
author={Tseng, Paul and Yun, Sangwoon},
journal={Math. Program.},
volume={117},
pages={387--423},
year={2009}
}

@article{PT09a,
title={Block-Coordinate Gradient Descent Method for Linearly
Constrained Nonsmooth Separable Optimization},
author={Tseng, Paul and Yun, Sangwoon},
journal={Journal of Optimization Theory and Applications},
volume={140},
pages={513--535},
year={2009}
}

@Article{PT10a,
author="Tseng, Paul and Yun, Sangwoon",
title="A coordinate gradient descent method for linearly constrained smooth optimization and support vector machines training",
journal="Computational Optimization and Applications",
year="2010",
volume="47",
number="2",
pages="179--206"
}

@Article{PT10a-short,
author="Tseng, Paul and Yun, Sangwoon",
title="A coordinate gradient descent method for linearly constrained smooth optimization and support vector machines training",
journal={Comput. Optim. Appl.},
year="2010",
volume="47",
number="2",
pages="179--206"
}

@article{AT21a,
author = {Tsitsulin, Anton and Munkhoeva, Marina and Mottin, Davide and Karras, Panagiotis and Oseledets, Ivan and M\"{u}ller, Emmanuel},
title = {{FREDE}: Anytime Graph Embeddings},
year = {2021},
volume = {14},
journal = {Proceedings of the VLDB Endowment},
pages = {1102--1110}
}

@InProceedings{IT04a,
author = {Ioannis Tsochantaridis and Thomas Hofmann and Thorsten Joachims 
and Yasemin Altun},
title = {Support Vector Machine Learning for Interdependent and Structured 
Output Spaces},
booktitle = {ICML},
year = {2004}
}

@Article{IT05a-short,
  author =   {Ioannis Tsochantaridis and Thorsten Joachims and Thomas
Hofmann and Yasemin Altun},
  title =    {Large margin methods for structured and interdependent
output variables},
  journal =      {JMLR},
  year =     {2005},
  OPTvolume =    {6},
  OPTpages =     {1453--1484},
}

@Article{IT05a,
  author =   {Ioannis Tsochantaridis and Thorsten Joachims and Thomas
Hofmann and Yasemin Altun},
  title =    {Large margin methods for structured and interdependent
output variables},
  journal =      {Journal of Machine Learning Research},
  year =     {2005},
  volume =	 {6},
  pages =	 {1453--1484}
}

@ARTICLE{GT07a,
title = {Multi-Label Classification: An Overview},
author = {Tsoumakas, Grigorios and Katakis, Ioannis},
year = {2007},
journal = {International Journal of Data Warehousing and Mining},
volume = {3},
pages = {1--13}
}

@inproceedings{GT07b,
  title={Random k-labelsets: An ensemble method for multilabel classification},
  author={Tsoumakas, Grigorios and Vlahavas, Ioannis},
  booktitle={European Conference on Machine Learning},
  pages={406--417},
  year={2007}
}

@InProceedings{GT08a,
  author = 	 {Grigorios Tsoumakas and Ioannis Katakis and Ioannis Vlahavas},
  title = 	 {Effective and Efficient Multilabel Classification in Domains with Large Number of Labels},
  OPTcrossref =  {},
  OPTkey = 	 {},
  booktitle =	 {Proceedings of ECML/PKDD 2008 Workshop on Mining Multidimensional Data},
  OPTyear = 	 {},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTpages = 	 {},
  OPTmonth = 	 {},
  OPTaddress = 	 {},
  OPTorganization = {},
  OPTpublisher = {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@article{GT10a,
author="Tsoumakas, Grigorios and Katakis, Ioannis and Vlahavas, Ioannis",
title="Mining Multi-label Data",
journal="Data Mining and Knowledge Discovery Handbook",
year="2010",
pages="667--685"
}

@article{GT11a,
  author       = {Grigorios Tsoumakas and Eleftherios Spyromitros-Xioufis and Jozef Vilcek and Ioannis Vlahavas},
  title        = {Mulan: A {J}ava Library for Multi-Label Learning},
  journal      = {Journal of Machine Learning Research},
  year         = {2011},
  volume       = {12},
  pages        = {2411--2414}
}

@InProceedings{HHT10a,
  author = {Han-Hsing Tu and Hsuan-Tien Lin},
  title = {One-sided Support Vector Regression for Multiclass Cost-sensitive Classification},
  booktitle = {Proceedings of the Twenty Seventh International Conference on Machine Learning (ICML)},
  year = {2010},
  url = {http://www.csie.ntu.edu.tw/~htlin/paper/doc/icml10osr.pdf}
}

@inproceedings{DT20a,
    title = "{LEDGAR}: A Large-Scale Multi-label Corpus for Text Classification of Legal Provisions in Contracts",
    author = {Tuggener, Don  and
      von D{\"a}niken, Pius  and
      Peetz, Thomas  and
      Cieliebak, Mark},
    editor = "Calzolari, Nicoletta  and
      B{\'e}chet, Fr{\'e}d{\'e}ric  and
      Blache, Philippe  and
      Choukri, Khalid  and
      Cieri, Christopher  and
      Declerck, Thierry  and
      Goggi, Sara  and
      Isahara, Hitoshi  and
      Maegaard, Bente  and
      Mariani, Joseph  and
      Mazo, H{\'e}l{\`e}ne  and
      Moreno, Asuncion  and
      Odijk, Jan  and
      Piperidis, Stelios",
    booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
    year = "2020",
    pages = "1235--1241",
}

@article{RST98a,
  title={{Parallel sparse matrix vector multiply software for matrices with data locality}},
  author={Tuminaro, R.S. and Shadid, J.N. and Hutchinson, S.A.},
  journal={Concurrency - Practice and Experience},
  volume={10},
  number={3},
  pages={229--247},
  year={1998}
}

@inproceedings{ST11a,
  title={Parallel boosted regression trees for web search ranking},
  author={Tyree, Stephen and Weinberger, Kilian Q and Agrawal, Kunal and Paykin, Jennifer},
  booktitle={Proceedings of the 20th International Conference on World Wide Web},
  pages={387--396},
  year={2011}
}


@incollection{NU03a,
  author    = "Naonori Ueda and Kazumi Saito",
  title     = "Parametric Mixture Models for Multi-Labeled Text",
  original  = "psgz/AA30.ps.gz",
  booktitle = "Advances in Neural Information Processing Systems 15",
  editor    = "S. Becker, S. Thrun and K. Obermayer",
  publisher = "MIT Press",
  address   = "Cambridge, MA",
  pages     = "721--728",
  year      = "2003",
}

@incollection{NU03a-short,
  author    = "Naonori Ueda and Kazumi Saito",
  title     = "Parametric Mixture Models for Multi-Labeled Text",
  booktitle = "{NIPS} 15",
  pages     = "721--728",
  year      = "2003"
}


@InProceedings{SU02a,
  author = 	 {Secil Ugurel and Robert Krovetz and
C. Lee Giles and
David M. Pennock and
Eric Glover and
Hongyuan Zha },
  title = 	 {What's the code? {A}utomatic Classification of Source Code Archives },
  booktitle = 	 {Proceedings of ACM KDD 2002}
}

@PhdThesis{MU02a,
  author = 	 {Michael Ulbrich},
  title = 	 {Nonsmooth Newton-like Methods for Variational Inequalities
and Constrained Optimization Problems in Function Spaces},
  school = 	 {Technische Universit\"{a}t M\"{u}nchen},
  year = 	 2000
}

@article{BU05a,
  title={Determination of optimal support vector regression parameters by genetic algorithms and simplex optimization},
  author={{\"U}st{\"u}n, B{\"u}lent and Melssen, Willem J. and Oudenhuijzen, Michiel K. and Buydens, Lutgarde Maria Celina},
  journal={Analytica Chimica Acta},
  volume={544},
  number={1-2},
  pages={292--305},
  year={2005}
}

@article{AVU06a,
	title       = {Detection of non-coding {RNA}s on the basis of predicted
	secondary structure formation free energy change},
	author      = {Andrew V Uzilov and Joshua M Keegan and David H Mathews},
	journal     = {BMC Bioinformatics},
	year        = {2006},
	volume      = {7},
	number      = {173},
	url         = {http://www.biomedcentral.com/1471-2105/7/173/}
}

@inproceedings{BV18a,
 author = {van Merrienboer, Bart and Moldovan, Dan and Wiltschko, Alexander},
 booktitle = {Advances in Neural Information Processing Systems},
 title = {Tangent: Automatic differentiation using source-code transformation for dynamically typed array programming},
 volume = {31},
 year = {2018}
}

@incollection{AV17a,
title = {Attention is All you Need},
author = {Vaswani, Ashish and Shazeer, Noam and Parmar, Niki and Uszkoreit, Jakob and Jones, Llion and Gomez, Aidan N and Kaiser, \L ukasz and Polosukhin, Illia},
booktitle = {Advances in Neural Information Processing Systems 30},
editor = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
pages = {5998--6008},
year = {2017}
}

@Article{SAV92a,
  author = 	 {S. A. Vavasis},
  title = 	 {Preconditioning for boundary integral equations},
  journal = 	 {SIAM J. Matrix Anal. Appl.},
  year = 	 {1992},
  volume =	 {13},
  pages =	 {905--925}
}

@inproceedings{AV15a,
   title={Mat{C}onv{N}et: Convolutional neural networks for matlab},
   author={Vedaldi, Andrea and Lenc, Karel},
   booktitle={Proceedings of the 23rd ACM International Conference on  
Multimedia},
   pages={689--692},
   year={2015}
}

@inproceedings{SV05a,
  title={Hierarchical {D}irichlet Model for Document Classification},
  author={Veeramachaneni, S. and Sona, D. and Avesani, P.},
  booktitle={Proceedings of the 22nd international conference on Machine 
learning},
  pages={928--935},
  year={2005},
  publisher={ACM Press New York, NY, USA}
}

@Book{WNC02a,
  author =	 {W. N. Venables and B. D. Ripley},
  title = 	 {Modern Applied Statistics with {S}},
  publisher = 	 {Springer-Verlag},
  year = 	 2002,
  address =	 {New York},
  edition =	 {Fourth},
}


@InProceedings{HPV02a,
  author = 	 {Jean-Philippe Vert},
  title = 	 {Support vector machine prediction of signal peptide cleavage site using a new class of kernels for strings},
  booktitle = 	 {Proceedings of the Pacific Symposium on Biocomputing 2002},
  pages =	 {649--660},
  year =	 {2002},
  editor =	 {Altman, R.B. and  Dunker, A.K. and  Hunter, L. and  Lauerdale, K. and Klein, T.E.},
  publisher =	 {World Scientific}
}





@Misc{TRON00a,
  title =	 {{NEOS} {AMPL} Interfaces to {TRON}},
  note =	 {Software available at {\tt http://neos.mcs.anl.gov/neos/solvers/BCO:TRON-AMPL/}}
}

@Article{RJV86a,
  author = 	 {R.J. Vanderbei and M.S. Meketon and B.A. Freedman},
  title = 	 {A modification of {K}armarkar's linear programming algorithm},
  journal = 	 {Algorithmica},
  year = 	 {1986},
  volume =	 {1},
  pages =	 {395--407}
}

@TechReport{RV94a,
  author = 	 {Robert Vanderbei},
  title = 	 {{LOQO}: An Interior Point Code
     for Quadratic Programming},
  institution =  {Statistics and Operations Research, Princeton University},
  year = 	 {1994},
  number =	 {SOR 94-15},
  note =	 {revised November, 1998}
}

@TechReport{LV94,
  author = 	 {L. Vandenberghe and S. Boyd},
  title = 	 {{SP}: Software for Semidefinite Programming},
  institution =  {Department of Electrical Engineering, Stanford University},
  year = 	 {1994},
  month =	 {November},
  note =	 {Available at http://www-ISL.Stanford.EDU/people/boyd/SP.html}
}

@article{LV96,
author     = {L. Vandenberghe and S. Boyd},
journal    = {SIAM Rev.},
pages      = {49--95},
title      = {Semidefinite Programming},
volume     = {38},
year       = {1996}
}

@article{DL80a,
title={Simultaneous rayleigh-quotient minimization methods for< i> Ax= $\lambda$Bx</i>},
author={Longsine, Dennis and McCormick, Stephen Fahrney},
journal={Linear Algebra and its Applications},
volume={34},
pages={195--234},
year={1980},
publisher={Elsevier}
}

@TechReport{RJV97a,
  author = 	 {Robert J. Vanderbei and David F. Shanno},
  title = 	 {An interior point algorithm for nonconvex nonlinear programming},
  institution =  {Statistics and Operations Research, Princeton University},
  year = 	 {1997},
  number =	 {SOR-97-21}
}

@Article{AVDS69,
  author = 	 {A. van der Sluis},
  title = 	 {Condition numbers and equilibration of matrices},
  journal = 	 {Numer. Math.},
  year = 	 {1969},
  volume =	 {14},
  pages =	 {14--23}
}


@Book{VV79a,
  author = 	 "V. Vapnik",
  title = 	 "Estimation of Dependences Based on Empirical Data",
  publisher = 	 "Springer Verlag",
  year = 	 "1982",
  address =	 "New York, NY"
}

@Book{VV95a,
  author = 	 {Vladimir Vapnik},
  title = 	 {The Nature of Statistical Learning Theory},
  publisher = 	 {Springer-Verlag},
  year = 	 {1995},
  address =      {New York, NY}
}

@Book{VV98a,
  author = 	 {Vladimir Vapnik},
  title = 	 {Statistical Learning Theory},
  publisher = 	 {Wiley},
  address =      {New York, NY},
  year = 	 {1998}
}

@Book{VV98a-short,
  author = 	 {Vladimir Vapnik},
  title = 	 {Statistical Learning Theory},
  year = 	 {1998}
}

@InProceedings{Vapnik00a,
  author        = {V.~Vapnik and O.~Chapelle},
  title         = {Bounds on error expectation for {SVM}},
  pages         = {261--280},
  publisher     = {{MIT} Press},
  year          = {2000},
  booktitle     = {Advances in Large Margin Classifiers},
  editor        = {A.J.~Smola and P.L.~Bartlett and B.~Sch{\"o}lkopf and
                  D.~Schuurmans},
  address       = {Cambridge, MA},
}

@article{VV00b,
    author = "Vladimir Vapnik and Olivier Chapelle",
    title = "Bounds on Error Expectation for Support Vector Machines",
    journal = "Neural Computation",
    volume = "12",
    number = "9",
    pages = "2013--2036",
    year = "2000",
    url = "citeseer.nj.nec.com/vapnik99bounds.html" 
}

@TechReport{LVA02a,
  author =  {Luis von Ahn and  Manuel Blum and John Langford},
  title =   {Telling Humans and Computers Apart (Automatically) or How Lazy Cryptographers do {AI}},
  institution =  {Computer Science Department, Carnegie Mellon University, Pittsburgh},
  year =     {2002},
  number =   {CMU-CS-02-117},
  url =     {http://www.cs.cmu.edu/~biglou/captcha.pdf}
}


@article{JPV83a,
  title={Strong and weak convexity of sets and functions},
  author={Jean-Philippe Vial},
  journal={Mathematics of Operations Research},
  volume={8},
  number={2},
  pages={231--259},
  year={1983}
}


@inproceedings{OV12a,
   title={Krylov subspace descent for deep learning},
   author={Vinyals, Oriol and Povey, Daniel},
   booktitle={Proceedings of Artificial Intelligence and Statistics},
   pages={1261--1268},
   year={2012}
}

@InProceedings{SVNV06a,
  author =       {S.V.N. Vishwanathan and Nicol N. Schraudolph and Mark W. Schmidt and Kevin Murphy},
  title =        {Accelerated Training of Conditional Random Fields with Stochastic Gradient Methods},
  booktitle =    {Proceedings of the Twenty Third International Conference on Machine Learning (ICML)},
  year =         {2006},
  pages =        {969--976}
}

@Article{AJV67a,
  author    = {Andrew J. Viterbi},
  title     = {Error bounds for convolutional codes and an
asymptotically optimal decoding algorithm},
  year      = {1967},
  journal   = {IEEE Transactioins on Information Theory},
  pages     = {260--269},
  volume    = {13},
  number    = {2},
}


@article{TPV88a,
year={1988},
journal={Biological Cybernetics},
volume={59},
number={4-5},
title={Accelerating the convergence of the back-propagation method},
publisher={Springer-Verlag},
author={Vogl, T.P. and Mangis, J.K. and Rigler, A.K. and Zink, W.T. and Alkon, D.L.},
pages={257-263},
}

@TechReport{LVA02a-short,
  author =  {Luis von Ahn and  Manuel Blum and John Langford},
  title =   {Telling Humans and Computers Apart (Automatically) or How Lazy Cryptographers do {AI}},
  number =   {CMU-CS-02-117},
  year =     {2002}
}

@inproceedings{TV20a,
  title     = {A Label Attention Model for {ICD} Coding from Clinical Text},
  author    = {Vu, Thanh and Nguyen, Dat Quoc and Nguyen, Anthony},
  booktitle = {Proceedings of the Twenty-Ninth International Joint Conference on
               Artificial Intelligence (IJCAI)},
  pages     = {3335--3341},
  year      = {2020},
  doi       = {10.24963/ijcai.2020/461}
}

@InProceedings{GW00a,
  author =      {G. Wahba and Y. Lin and H. Zhang},
  title =       {Generalized approximate cross validation for support vector
                 machines},
  booktitle =   {Advances in Large Margin Classifiers},
  editor =      {A.J.~Smola and P.L.~Bartlett and B.~Sch{\"o}lkopf and
                 D.~Schuurmans},
  pages =       {297--309},
  year = {2000},
  publisher = {MIT Press},
  url = {ftp://ftp.stat.wisc.edu/pub/wahba/svm.ps}
}

@InProceedings{GW98a,
  author =      {G. Wahba},
  title =       {Support vector machines, reproducing kernel {H}ilbert spaces,
                 and randomized {GACV}},
  booktitle =   {Advances in Kernel Methods: Support Vector Learning},
  editor =      {Bernhard Sch\"{o}lkopf and Christopher J. C. Burges and
                 Alexander J. Smola},
  pages =       {69--88},
  year = {1998},
  publisher = {MIT Press},
  url = {ftp://ftp.stat.wisc.edu/pub/wahba/nips97rr.ps}
}

@InProceedings{YW23a,
author="Wahba, Yasmen
and Madhavji, Nazim
and Steinbacher, John",
title="A Comparison of SVM Against Pre-trained Language Models (PLMs) for Text Classification Tasks",
booktitle="Machine Learning, Optimization, and Data Science",
year="2023",
publisher="Springer Nature Switzerland",
pages="304--313"
}

@article{JMW05a,
  title={A note on trust-region radius update},
  author={Walmag, J{\'e}r{\^o}me MB and Delhez, {\'E}ric JM},
  journal={SIAM Journal on Optimization},
  volume={16},
  number={2},
  pages={548--562},
  year={2005}
}

@article{JMW05a-short,
  title={A note on trust-region radius update},
  author={Walmag, J{\'e}r{\^o}me MB and Delhez, {\'E}ric JM},
  journal={SIAM J. Optim.},
  volume={16},
  number={2},
  pages={548--562},
  year={2005}
}

@inproceedings{AW19a,
    title = "{GLUE}: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding",
    author = "Wang, Alex  and
      Singh, Amanpreet  and
      Michael, Julian  and
      Hill, Felix  and
      Levy, Omer  and
      Bowman, Samuel",
    booktitle = "Proceedings of the {EMNLP} Workshop {B}lackbox{NLP}: Analyzing and Interpreting Neural Networks for {NLP}",
    year = "2018",
    pages = "353--355"
}

@inproceedings{BW19a,
    title = "Ranking-Based Autoencoder for Extreme Multi-label Classification",
    author = "Wang, Bingyu  and
      Chen, Li  and
      Sun, Wei  and
      Qin, Kechen  and
      Li, Kefeng  and
      Zhou, Hui",
    booktitle = "Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics (NAACL)",
    year = "2019",
    pages = "2820--2830"
}


@Article{CCW15a,
  author = 	 {Chien-Chih Wang and Chun-Heng Huang and Chih-Jen Lin},
  title = 	 {Subsampled {H}essian {N}ewton Methods for Supervised Learning},
  journal = {Neural Computation},
  year = 	 {2015},
  OPTkey = 	 {},
  volume =	 {27},
  number =	 {8},
  pages =	 {1766--1795},
  OPTmonth = 	 {},
  publisher = {MIT Press},  
  url={http://www.csie.ntu.edu.tw/~cjlin/papers/sub_hessian/sample_hessian.pdf},  
  OPTannote = 	 {}
}

@Article{CCW15a-short,
  author = 	 {Chien-Chih Wang and Chun-Heng Huang and Chih-Jen Lin},
  title = 	 {Subsampled {H}essian {N}ewton Methods for Supervised Learning},
  journal = {Neural Comput.},
  year = 	 {2015},
  volume =	 {27},
  pages =	 {1766--1795},
}

@Article{CCW16a,
author={Chien-Chih Wang and Kent-Loong Tan and Chun-Ting Chen and Yu-Hsiang Lin and
S. Sathiya Keerthi and Dhruv Mahajan and 
Sellamanickam Sundararajan and Chih-Jen Lin},
title={Distributed {N}ewton Methods for Deep Learning},
journal = {Neural Computation},
year={2018},
volume =	 {30},
pages =	 {1673--1724},
url={http://www.csie.ntu.edu.tw/~cjlin/papers/dnn/dsh.pdf},
number =   {6}
}

@Article{CCW16a-short,
author={Chien-Chih Wang and Kent-Loong Tan and Chun-Ting Chen and Yu-Hsiang Lin and
S. Sathiya Keerthi and Dhruv Mahajan and 
Sellamanickam Sundararajan and Chih-Jen Lin},
title={Distributed {N}ewton Methods for Deep Learning},
journal     ={Neural Comput.},
year={2018},
volume =	 {30},
pages =	 {1673--1724},
}

@article{CCW18a,
author = {Wang, Chien-Chih and Tan, Kent Loong and Lin, Chih-Jen},
title = {Newton Methods for Convolutional Neural Networks},
journal = {ACM Transactions on Intelligent Systems and Technology},
year = {2020},
volume = {11},
number = {2},
pages = {19:1--19:30},
url = {https://www.csie.ntu.edu.tw/~cjlin/papers/cnn/newton-CNN.pdf}
}

@article{CCW18a-short,
author = {Wang, Chien-Chih and Tan, Kent Loong and Lin, Chih-Jen},
title = {Newton Methods for Convolutional Neural Networks},
journal = {ACM TIST},
year = {2020},
volume = {11},
pages = {19:1--19:30}
}

@inproceedings{GW18a,
  title={Joint Embedding of Words and Labels for Text Classification},
  author={Guoyin Wang and Chunyuan Li and Wenlin Wang and Yizhe Zhang and Dinghan Shen and Xinyuan Zhang and Ricardo Henao and Lawrence Carin},
  booktitle =    {Proceedings of the 56th Annual Meeting of the Association of Computational Linguistics (ACL)},
  doi = "10.18653/v1/P18-1216",  
  year={2018}
}

@MastersThesis{HJW08a,
  author =   {Hsiang-Jui Wang},
  title =    {Applying Automatic Differentiation and Truncated Newton Methods to
              Conditional Random Fields},
  school =   {Department of Computer Science and Information
Engineering, National Taiwan University},
  year =     {2008}
}


@MastersThesis{JYW02a,
  author = 	 {Jung-Ying Wang},
  title = 	 {Application of Support Vector Machines in Bioinformatics},
  school = 	 {Department of Computer Science and Information Engineering, National Taiwan University},
  year = 	 {2002}
}




@Article{PWW13a,
  author = 	 {Po-Wei Wang and Chih-Jen Lin},
  title = 	 {Iteration Complexity of Feasible Descent Methods for Convex Optimization},
  journal = 	 {Journal of Machine Learning Research},
  year = 	 {2014},
 volume = {15},
  pages={1523--1548},
  url={http://www.csie.ntu.edu.tw/~cjlin/papers/cdlinear.pdf},
  OPTkey = 	 {},
  OPTtype = 	 {},
  OPTnumber = 	 {},
  OPTaddress = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@Article{PWW13a-short,
  author = 	 {Po-Wei Wang and Chih-Jen Lin},
  title = 	 {Iteration Complexity of Feasible Descent Methods for Convex Optimization},
  journal = 	 {JMLR},
  year = 	 {2014},
 volume = {15},
  pages={1523--1548}
}

@article{PWW14a,
  author = 	 {Po-Wei Wang and Chih-Jen Lin},
  title = 	 {Iteration Complexity of Feasible Descent Methods for Convex Optimization},
  journal=	 {JMLR},
  year= 	 {2014}
}


@article{PWW15a,
  author = 	 {Po-Wei Wang and Ching-Pei Lee and Chih-Jen Lin},
  title   = {The Common-directions Method for Regularized Empirical Risk Minimization},
  journal = {Journal of Machine Learning Research},
  year    = {2019},
  volume  = {20},
  number  = {58},
  pages   = {1-49},
  url     = {https://www.csie.ntu.edu.tw/~cjlin/papers/commdir/commdir.pdf},
  OPTkey = 	 {},
  OPTtype = 	 {},
  OPTnumber = 	 {},
  OPTaddress = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@article{PWW15a-short,
  author = 	 {Po-Wei Wang and Ching-Pei Lee and Chih-Jen Lin},
  title   = {The Common-directions Method for Regularized Empirical Risk Minimization},
  journal = {JMLR},
  year    = {2019},
  volume  = {20},
  pages   = {1-49}
}

@inproceedings{QHW04a,
  title={Visual Object Recognition Through One-Class Learning},
  author={Wang, QingHua and Lopes, Lu{\'\i}s Seabra and Tax, David M. J.},
  booktitle={Image Analysis and Recognition},
  pages={463--470},
  year={2004},
  publisher={Springer}
}

@inproceedings{SW10a,
 author = {Wang, Shuangquan and Chen, Canfeng and Ma, Jian},
 title = {Accelerometer Based Transportation Mode Recognition on Mobile Phones},
 booktitle = {Proceedings of the 2010 Asia-Pacific Conference on Wearable Computing Systems},
 year = {2010},
 pages = {44--46}
}

@incollection{SW18a,
title = {{GIANT}: Globally Improved Approximate {N}ewton Method for Distributed Optimization},
author = {Wang, Shusen and Roosta-Khorasani, Farbod and Xu, Peng and Mahoney, Michael W.},
booktitle = {Advances in Neural Information Processing Systems},
editor = {S. Bengio and H. Wallach and H. Larochelle and K. Grauman and N. Cesa-Bianchi and R. Garnett},
pages = {2332--2342},
year = {2018}
}

@incollection{SW18a-short,
title = {{GIANT}: Globally Improved Approximate {N}ewton Method for Distributed Optimization},
author = {Wang, Shusen and Roosta-Khorasani, Farbod and Xu, Peng and Mahoney, Michael W.},
booktitle = {NIPS},
year = {2018}
}

@inproceedings{SEW12a,
 author = {Whang, Steven Euijong and Garcia-Molina, Hector},
 title = {Joint Entity Resolution},
 booktitle = {Proceedings of the 2012 IEEE 28th International Conference on Data Engineering},
 year = {2012},
 pages = {294--305},
} 

@article{SEW13a,
 author = {Whang, Steven Euijong and Marmaros, David and Garcia-Molina, Hector},
 title = {Pay-As-You-Go Entity Resolution},
 journal = {IEEE Transactions on Knowledge and Data Engineering},
 volume = {25},
 number = {5},
 year = {2013},
 pages = {1111--1124},
}

@InProceedings{SBR13a,
author = {Senjuti B. Roy and Martine D. Cock and Vani Mandava and Brian Dalessandro and Claudia Perlich and William Cukierski and Ben Hamner},
title = {The {M}icrosoft Academic Search Dataset and {KDD} {C}up 2013},
booktitle = {Proceedings of the KDD Cup 2013 Workshop},
pages = {1:1--1:6},
publisher = {ACM},
year = {2013},
}

@inproceedings{LW13a,
  title={Regularization of neural networks using {D}rop{C}onnect},
  author={Wan, Li and Zeiler, Matthew and Zhang, Sixin and {LeCun}, Yann
and Fergus, Rob},
  booktitle={Proceedings of the 30th International Conference on Machine
Learning (ICML)},
  pages={1058--1066},
  year={2013}
}

@article{SW20a,
  title={Multi-task learning based network embedding},
  author={Wang, Shanfeng and Wang, Qixiang and Gong, Maoguo},
  journal={Frontiers in Neuroscience},
  volume={13},
  pages={1387},
  year={2020}
}

@inproceedings{SW12a,
    title = "Baselines and Bigrams: Simple, Good Sentiment and Topic Classification",
    author = "Wang, Sida  and
      Manning, Christopher",
    booktitle = "Proceedings of the Fiftieth Annual Meeting of the Association for Computational Linguistics (ACL)",
    year = "2012",
    pages = "90--94",
}

@INPROCEEDINGS{XW11b,
  author={Wang, Xi and Sukthankar, Gita},
  booktitle={Proceedings of IEEE Third International Conference on Privacy, Security, Risk and Trust, and IEEE Third International Conference on Social Computing}, 
  title={Extracting Social Dimensions Using Fiedler Embedding}, 
  year={2011},
  pages={824--829}
}

@inproceedings{XW13a,
author = {Wang, Xi and Sukthankar, Gita},
title = {Multi-Label Relational Neighbor Classification Using Social Context Features},
year = {2013},
booktitle = {Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)},
pages = {464--472}
}

@Article{XW97a,
  author = 	 {Xiaoge Wang and Kyle A. 
Gallivan and Randall Bramley},
  title = 	 {{CIMGS}: an incomplete orthogonal factorization preconditioner},
  journal = 	 {SIAM J. Sci. Comput.},
  year = 	 {1997},
  volume =	 {18},
  number =	 {2},
  pages =	 {516--536}
}

@inproceedings{XW19a,
title={Doubly robust joint learning for recommendation on data missing not at random},
author={Wang, Xiaojie and Zhang, Rui and Sun, Yu and Qi, Jianzhong},
booktitle={International Conference on Machine Learning},
pages={6638--6647},
year={2019}
}

@inproceedings{XW19a-short,
title={Doubly robust joint learning for recommendation on data missing not at random},
author={Wang, Xiaojie and Zhang, Rui and Sun, Yu and Qi, Jianzhong},
booktitle={ICML},
year={2019}
}

@article{XW11a,
	title={Theoretical analysis for solution of support vector data description},
	author={Wang, Xiaoming and Chung, Fu-lai and Wang, Shitong},
	journal={Neural Networks},
	volume={24},
	number={4},
	pages={360--369},
	year={2011},
	publisher={Elsevier}
}

@inproceedings{XW16a,
title={Learning to rank with selection bias in personal search},
author={Wang, Xuanhui and Bendersky, Michael and Metzler, Donald and Najork, Marc},
booktitle={Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval},
pages={115--124},
year={2016}
}

@inproceedings{XW16a-short,
title={Learning to rank with selection bias in personal search},
author={Wang, Xuanhui and Bendersky, Michael and Metzler, Donald and Najork, Marc},
booktitle={SIGIR},
year={2016}
}

@inproceedings{XW18a,
title={Position bias estimation for unbiased learning to rank in personal search},
author={Wang, Xuanhui and Golbandi, Nadav and Bendersky, Michael and Metzler, Donald and Najork, Marc},
booktitle={Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining},
pages={610--618},
year={2018}
}

@inproceedings{XW18a-short,
title={Position bias estimation for unbiased learning to rank in personal search},
author={Wang, Xuanhui and Golbandi, Nadav and Bendersky, Michael and Metzler, Donald and Najork, Marc},
booktitle={WSDM},
year={2018}
}

@article{XW13b,
  title={Learning with multi-resolution overlapping communities},
  author={Wang, Xufei and Tang, Lei and Liu, Huan and Wang, Lei},
  journal={Knowledge and Information Systems},
  volume={36},
  pages={517--535},
  year={2013}
}

@inproceedings{YW20a,
author = {Wang, Yaojing and Pan, Guosheng and Yao, Yuan and Tong, Hanghang and Yang, Hongxia and Xu, Feng and Lu, Jian},
title = {Bringing Order to Network Embedding: A Relative Ranking Based Approach},
year = {2020},
booktitle = {Proceedings of the 29th ACM International Conference on Informationand Knowledge Management (CIKM)},
pages = {1585--1594}
}

@InProceedings{YW09a,
  title = 	 {{PLDA}: Parallel latent {D}irichlet allocation for large-scale applications},
  author = 	 {Wang, Yi and Bai, Hongjie and Stanton, Matt and Chen, Wen-Yen and Chang, Edward Y.},
  OPTcrossref =  {},
  OPTkey = 	 {},
  booktitle =	 {International Conference on Algorithmic Aspects in Information and Management},
  OPTpages = 	 {},
  year =	 {2009},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTaddress = 	 {},
  OPTmonth = 	 {},
  OPTorganization = {},
  OPTpublisher = {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@article{MW00a,
	title={{Large-scale controlled vocabulary indexing for named entities}},
	author={Wasson, M.},
	journal={Proceedings of the sixth conference on Applied natural language processing},
  pages={276--281},
  year={2000},
  publisher={Morgan Kaufmann Publishers Inc. San Francisco, CA, USA}
}


@Article{JWW81a,
  author = 	 {Watts, III, James W.},
  title = 	 {A conjugate graduent-truncated 
direct method for the iterative solution of the 
reservoir simulation pressure equation},
  journal = 	 {Soc. Pet. Eng. J.},
  year = 	 {1981},
  volume =	 {21},
  pages =	 {345--353}
}

@inproceedings{ST06a,
   author    = {Steve Webb and James Caverlee and Calton Pu},   
   title     = {Introducing the Webb Spam Corpus: Using Email Spam to Identify Web Spam Automatically},
   booktitle = {Proceedings of the Third Conference on Email and Anti-Spam (CEAS)},
   year      = {2006}
}

@inproceedings{TW18a,
  title     = {Does Tail Label Help for Large-Scale Multi-Label Learning},
  author    = {Tong Wei and Yu-Feng Li},
  booktitle = {Proceedings of the Twenty-Seventh International Joint Conference on
               Artificial Intelligence (IJCAI)},
  pages     = {2847--2853},
  year      = {2018},
  doi       = {10.24963/ijcai.2018/395}
}

@inproceedings{TW19a,
title={Learning Compact Model for Large-Scale Multi-Label Data},
DOI={10.1609/aaai.v33i01.33015385},
booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
author={Wei, Tong and Li, Yu-Feng},
year={2019},
pages={5385-5392}
}

@inproceedings{TW21a,
author = {Wei, Tong and Tu, Wei-Wei and Li, Yu-Feng and Yang, Guo-Ping},
title = {Towards Robust Prediction on Tail Labels},
year = {2021},
booktitle = {Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)},
pages = {1812--1820}
}

@Book{ASW94a,
  editor =	 {A. S. Weigend and N. A. Gershenfeld},
  title = 	 {Time series prediction: forcasting the future and understanding the past},
  publisher = 	 {Addison-Wesley},
  year = 	 {1994}
}

@inproceedings{KW09a,
  author = {Weinberger, Kilian and Dasgupta, Anirban and Langford,
John and Smola, Alex and Attenberg, Josh},
  title = {Feature Hashing for Large Scale Multitask Learning},
  booktitle = {Proceedings of the Twenty Sixth International Conference
on Machine Learning (ICML)},
  year = {2009},
  pages = {1113--1120}
}

@article{MPW01a,
	title={Designing the market game for a trading agent competition},
	author={Michael P. Wellman and Peter R. Wurman and Kevin O'Malley and Roshan
	Bangera and Shou-De Lin and Daniel Reeves and William E. Walsh},
	journal={IEEE Internet Computing},
	volume={5},
	number={2},
	pages={43--51},
	year={2001},
	publisher={IEEE}
}

@Book{SW85a,
  author =	 {Sanford Weisberg},
  title = 	 {Applied Linear Regression},
  publisher = 	 {John Wiley and Sons},
  year = 	 {1985},
  OPTkey = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTaddress = 	 {},
  OPTedition = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}


@inproceedings{ZW17a,
      title={Improving Efficiency of SVM k-fold Cross-validation by Alpha Seeding},
        author={Wen, Zeyi and Li, Bin and Kotagiri, Ramamohanarao and Chen, Jian and Chen, Yawen and Zhang, Rui},
          booktitle={Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence},
            year={2017}
}


@InProceedings{JYW11a,
  author    = {Jui-Yu Weng and Cheng-Lun Yang and Bo-Nian Chen and Yen-Kai Wang and Shou-De Lin},
  title     = {{IMASS}: An Intelligent Microblog Analysis and Summarization System},
  booktitle = {Proceedings of the ACL-HLT 2011 System Demonstrations},
  year      = {2011},
  pages     = {133--138}
}


@Article{RCW10a,
author      = {Ruby C. Weng},
journal     = {Bayesian Analysis},
title       = {A {B}ayesian {E}dgeworth expansion by {S}tein's {I}dentity},
volume={5},
number={4},
pages       = {741--764},
year        = {2010}
}


@Article{RCW11a,
  author = 	 {Ruby C. Weng and Chih-Jen Lin},
  title = 	 {A {B}ayesian Approximation Method for Online Ranking},
  journal = 	 {Journal of Machine Learning Research},
  year = 	 {2011},
  OPTkey = 	 {},
  volume =	 {12},
  OPTnumber = 	 {},
  pages =	 {267--300},
  url = {http://www.csie.ntu.edu.tw/~cjlin/papers/online_ranking/online_journal.pdf},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@article{we:in,
author      = {Ruby C. Weng and Michael Woodroofe},
journal     = {Statistica Sinica},
pages       = {693--713},
title       = {Integrable expansions for posterior distributions
               for multiparameter exponential families
               with applications to sequential confidence levels},
volume      = {10},
year        = {2000}
}


@article{REW64a,
  title={A simple automatic derivative evaluation program},
  author={Wengert, Robert Edwin},
  journal={Communications of the ACM},
  volume={7},
  number={8},
  pages={463--464},
  year={1964}
}


@article{MW01a, 
 title={Predicting the clinical status of human breast cancer by using gene 
expression profiles}, 
 author={West, M. and Blanchette, C. and Dressman, H. and Huang, E. and Ishida, S. and 
Spang, R. and Zuzan, H. and J. A. {Olson, Jr.} and Marks, J. R. and Nevins, J. R.}, 
 journal={Proceedings of the National Academy of Sciences}, 
 volume={98}, 
 number={}, 
 pages={11462--11467}, 
 year={2001} 
} 


@TechReport{JW98a,
  author = 	 {J. Weston and C. Watkins},
  title = 	 {Multi-Class Support
          Vector Machines},
  institution =  {Royal Holloway},
  year = 	 {1998},
  number =	 {CSD-TR-98-04}
}




@InProceedings{JW99a,
  author = 	 {J. Weston and  C. Watkins},
  title = 	 {Multi-Class Support Vector Machines},
  booktitle = 	 {Proceedings of ESANN99},
  editor =	 {M. Verleysen},
  pages = 	 {219--224},
  address =	 {Brussels},
  publisher =	 {D. Facto Press},
  year = 	 {1999}
}

@InProceedings{JW99a-short,
  author = 	 {J. Weston and  C. Watkins},
  title = 	 {Multi-Class Support Vector Machines},
  booktitle = 	 {ESANN},
  pages = 	 {219--224},
  year = 	 {1999}
}

@inproceedings{JW00a,
    author = "Jason Weston and Sayan Mukherjee and Olivier Chapelle and Massimiliano Pontil and Tomaso Poggio and Vladimir Vapnik",
    title = "Feature Selection for {SVMs}",
  booktitle = 	 {Advances in Neural Information
Processing Systems},
    pages = "668--674",
    year = "2000",
    volume={12},
    url = "citeseer.nj.nec.com/article/weston01feature.html" 
}

@Misc{JW01a,
  author = 	 {J. Weston},
  year = {2001},
  note =	 {Private communication}
}

@InProceedings{JW13a,
  title = 	 {Label Partitioning For Sublinear Ranking},
  author = 	 {Weston, Jason and Makadia, Ameesh and Yee, Hector},
  booktitle = 	 {Proceedings of the 30th International Conference on Machine Learning (ICML)},
  pages = 	 {181--189},
  year = 	 {2013}
}

@article{RCW97a,
  title={Automated empirical optimizations of software and the ATLAS project},
  author={Whaley, R. Clint and Petitet, Antoine and Dongarra, Jack J.},
  journal={Parallel Computing},
  volume={27},
  pages={3--35},
  year={2001}
}

@article{RCW97a-short,
  title={Automated empirical optimizations of software and the ATLAS project},
  author={Whaley, R. Clint and Petitet, Antoine and Dongarra, Jack J.},
  journal={Parallel Comput.},
  volume={27},
  pages={3--35},
  year={2001}
}

@book{TW10a,
  title={{H}adoop: the definitive guide},
  author={White, Tom},
  year={2012},
  edition  = {Third},
  publisher={O'Reilly Media}
}

@inproceedings{RWW13a,
 author = {White, Ryen W. and Chu, Wei and Hassan, Ahmed and He, Xiaodong and Song, Yang and Wang, Hongning},
 title = {Enhancing Personalized Search by Mining and Modeling Task Behavior},
 booktitle = {Proceedings of the 22nd International Conference on World Wide Web (WWW)},
 year = {2013},
 pages = {1411--1420}
}

@inproceedings{RWW13a-short,
 author = {White, Ryen W. and Chu, Wei and Hassan, Ahmed and He, Xiaodong and Song, Yang and Wang, Hongning},
 title = {Enhancing Personalized Search by Mining and Modeling Task Behavior},
 booktitle = {WWW},
 year = {2013}
}

@inproceedings{PW12a,
  title={Transport mode detection with realistic smartphone sensor data},
  author={Widhalm, Peter and Nitsche, Philippe and Brandie, Norbert},
booktitle={Proceedings of the 21st International Conference on Pattern Recognition (ICPR)},
  pages={573--576},
  year={2012}
}



@InProceedings{BMW07a,
  author = 	 {Bogdan M. Wilamowski and Nicholas Cotton and Joel Hewlett and Okyay Kaynak},
  title = 	 {Neural Network Trainer with Second Order Learning Algorithms},
  OPTcrossref =  {},
  OPTkey = 	 {},
  booktitle =	 {In Proceedings of the 11th International Conference on Intelligent Engineering Systems},
  year =	 {2007},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTpages = 	 {},
  OPTmonth = 	 {},
  OPTaddress = 	 {},
  OPTorganization = {},
  OPTpublisher = {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@inproceedings{CW01a,
  author      = {Williams, Christopher~K.~I. and Seeger, Matthias},
  title       = {Using the {Nystr\"{o}m} Method to Speed Up Kernel Machines},
  booktitle   = {Neural Information Processing Systems 13},
  editor      = {Leen,~T. and Dietterich,~T. and Tresp,~V.},
  publisher   = {MIT Press},
  year        = {2001},
  pages       = {682--688}
}

@inproceedings{CW01a-short,
  author      = {Williams, Christopher~K.~I. and Seeger, Matthias},
  title       = {Using the {Nystr\"{o}m} Method to Speed Up Kernel Machines},
  booktitle   = {NIPS},
  year = {2001}
}

@inproceedings{ACW17a,
  title={The marginal value of adaptive gradient methods in machine learning},
  author={Wilson, Ashia C. and Roelofs, Rebecca and Stern, Mitchell and Srebro, Nati and Recht, Benjamin},
  booktitle={Advances in Neural Information Processing Systems},
  pages={4148--4158},
  year={2017}
}


@inproceedings{MW12a,
author      = {Martin Wistuba and Lars Schaefers and Marco Platzner},
booktitle   = {IEEE Conference on Computational Intelligence and Games},
pages       = {},
publisher   = {},
title       = {Comparison of {B}ayesian Move Prediction Systems for Computer {G}o
},
year        = {2012}
}


@Book{IW99,
  author =	 {Ian H. Witten and Eibe Frank and Mark A. Hall},
  title = 	 {Data Mining: Practical machine learning tools and techniques},
  publisher = 	 {Morgan Kaufmann},
  year = 	 {2011},
  edition = {Third},
  address =	 {San Francisco}
}



@Article{PW61a,
  author = 	 {P. Wolfe},
  title = 	 {A duality theorem for non-linear programming},
  journal = 	 {Quartely of Applied Mathematics},
  year = 	 {1961},
  volume =	 {19},
  pages =	 {239--244}
}

@Article{PW72a,
  author = 	 {P. Wolfe},
  title = 	 {On the convergence of gradient methods under constraint},
  journal = 	 {IBM J. Research and Development},
  year = 	 {1972},
  volume =	 {16},
  pages =	 {407--411}
}

@inproceedings{BW02a,
 author = {Ben Wolin},
 title = {Automatic classification in product catalogs},
 booktitle = {Proceedings of the 25th annual international ACM SIGIR conference on Research and development in information retrieval},
 series = {SIGIR '02},
 year = {2002},
 isbn = {1-58113-561-0},
 location = {Tampere, Finland},
 pages = {351--352},
 numpages = {2},
 doi = {10.1145/564376.564439},
 acmid = {564439},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {categorization, product classification, text classification},
}

@inproceedings{BW02a-short,
 author = {Ben Wolin},
 title = {Automatic classification in product catalogs},
 booktitle = {SIGIR},
 year = {2002},
 pages = {351--352}
} 

@techreport{MAW50a,
  title={Inverting modified matrices},
  author={Woodbury, Max A},
  volume={42},
  number={106},
  pages={336},
  year={1950},
  institution = {Statistical Research Group, Princeton University}
}

@techreport{MAW50a-short,
  title={Inverting modified matrices},
  author={Woodbury, Max A},
  number={106},
  year={1950},
  institution = {Princeton University}
}

@article{MW89a,
author      = {Michael Woodroofe},
journal     = {The Annals of Statistics},
pages       = {1087--1102},
title       = {Very weak expansions for sequentially designed experiments:
               linear models},
volume      = {17},
year        = {1989}
}

@article{wo:co,
author      = {Michael Woodroofe and D. Stephen Coad},
journal     = {Statistica Sinica},
pages       = {53--74},
title       = {Corrected confidence sets for sequentially designed experiments},
volume      = {7},
year        = {1997}
}

@Book{SW96a,
  author = 	 "Stephen J. Wright",
  title = 	 "Primal-Dual Interior-Point Methods",
  publisher = 	 "SIAM",
  year = 	 "1996"
}


@Article{SJW09a,
author = {Stephen J. Wright and Robert D. Nowak
and M\'{a}rio A.T. Figueiredo},
title = {Sparse Reconstruction by Separable
approximation},
journal = {IEEE Transactions on Signal Processing},
year = {2009},
pages = {2479--2493},
volume = {57}
}

@article{SJW10a,
title={Accelerated block-coordinate relaxation for regularized
optimization},
author={Wright, Stephen J},
journal={SIAM Journal on Optimization},
volume={22},
number={1},
pages={159--186},
year={2012},
publisher={SIAM}
}

@inproceedings{GW03a,
  title={Class-Boundary Alignment for Imbalanced Dataset Learning},
  author={Wu, Gang and Chang, Edward Y.},
  booktitle={ICML Workshop on Learning from Imbalanced Data Sets II},
  pages={49--56},
  year={2003}
}

@article{GW05a,
author={Wu, Gang and Chang, Edward Y.},
journal={IEEE Transactions on Knowledge and Data Engineering},
title={{KBA}: kernel boundary alignment considering imbalanced data distribution},
year={2005},
volume={17},
number={6},
pages={786--795}
}

@article{GW18b,
  title={Cost-sensitive multi-label learning with positive and negative label pairwise correlations},
  author={Guoqiang Wu and Yingjie Tian and Dalian Liu},
  journal={Neural networks},
  year={2018},
  volume={108},
  pages={411--423}
}

@inproceedings{KWW12a,
 author={Wu, Kuan-Wei and Ferng, Chun-Sung and Ho, Chia-Hua and Liang, An-Chun and Huang, Chun-Heng and Shen, Wei-Yuan and Jiang, Jyun-Yu and Yang, Ming-Hao and Lin, Ting-Wei and Lee, Ching-Pei and Kung, Perng-Hwa and Wang, Chin-En and Ku, Ting-Wei and Ho, Chun-Yen and Tai, Yi-Shu and Chen, I-Kuei and Huang, Wei-Lun and Chou, Che-Ping and Lin, Tse-Ju and Yang, Han-Jay and Wang, Yen-Kai and Li,Cheng-Te and Lin, Shou-De and Lin, Hsuan-Tien},
 title={A Two-Stage Ensemble of Diverse Models for Advertisement Ranking in {KDD} {C}up 2012},
 booktitle = {ACM SIGKDD KDD-Cup WorkShop},
 year = {2012}
}

@Article{SYW01a,
  author = 	 {Soon-Yi Wu and Shu-Cherng Fang and
Chih-Jen Lin},
  title = 	 {Solving the General Capacity 
Problem},
  journal = 	 {Annals of Operations 
Research},
  year = 	 {2001}, 
  volume={103},
  pages={193-211}
}

@InProceedings{SYW01b,
  author = {Soon-Yi Wu and Shu-Cherng Fang and Chih-Jen Lin},
  title = 	 {Analytic
    center based cutting plane method for linear semi-infinite
    programming}, 
  year = 	 {2001},
  editor =	 {M. Goberna and M. Lopez},
  publisher =	 {Kluwer},
  booktitle = 	 {Semi-infinite programming: recent
    advances}
}

@article{CHW07a,
  title={A real-valued genetic algorithm to optimize the parameters of support vector machine for predicting bankruptcy},
  author={Wu, Chih-Hung and Tzeng, Gwo-Hshiung and Goo, Yeong-Jia and Fang, Wen-Chang},
  journal={Expert Systems with Applications},
  volume={32},
  number={2},
  pages={397--408},
  year={2007}
}

@article{CHW09a,
  title={A Novel hybrid genetic algorithm for kernel function and parameter optimization in support vector regression},
  author={Wu, Chih-Hung and Tzeng, Gwo-Hshiung and Lin, Rong-Ho},
  journal={Expert Systems with Applications},
  volume={36},
  number={3},
  pages={4725--4735},
  year={2009}
}

@InProceedings{LW21a,
  title={Learning the Implicit Semantic Representation on Graph-Structured Data},
  author={Wu, Likang and Li, Zhi and Zhao, Hongke and Liu, Qi and Wang, Jun and Zhang, Mengdi and Chen, Enhong},
  booktitle = 	 {Proceedings of 26th International Conference on Database Systems for Advanced Applications},
  year={2021}
}

@incollection {TFW03a,
  author = "Ting-Fan Wu and  Chih-Jen Lin and  Ruby C. Weng",
  title = "Probability Estimates for Multi-Class Classification by Pairwise Coupling",
  booktitle = "Advances in Neural Information Processing Systems 16",
  editor = "Sebastian Thrun and Lawrence Saul and Bernhard {Sch\"{o}lkopf}",
  publisher = "MIT Press",
  address = "Cambridge, MA",
  year = "2004",
  keywords = "Markov chains, multi-class learning, multi-class prediction, optimization, support vector machines, voting methods",
  }



@incollection {TFW03a-short,
  author = " Ting-Fan Wu and  Chih-Jen Lin and  Ruby C. Weng",
  title = " Probability Estimates for Multi-Class Classification by Pairwise Coupling",
  booktitle = "{NIPS} 16",
  year = "2004"
  }

@Article{TFW03b,
  author = 	 {Ting-Fan Wu and
 Chih-Jen Lin and Ruby C. Weng},
  title = 	 {Probability Estimates for Multi-class Classification
by Pairwise Coupling},
  year =	 {2004},
 journal = {Journal of Machine Learning Research},
 volume={5},
 pages={975--1005},
 url =	 {http://www.csie.ntu.edu.tw/~cjlin/papers/svmprob/svmprob.pdf}
}


@Article{TTW08a,
  author = {Tong Tong Wu and Kenneth Lange}, 
  title = {Coordinate Descent Algorithms for Lasso Penalized Regression},

  journal = {The Annals of Applied Statistics},
  year = {2008},
  volume = {2},
  number = {1},
  pages = {224--244}
}

@InProceedings{XZW17a,
title = {A Unified View of Multi-Label Performance Measures},
author = {Xi-Zhu Wu and Zhi-Hua Zhou},
booktitle = {Proceedings of the 34th International Conference on Machine Learning (ICML)},
pages = {3780--3788},
year = {2017}
} 

@article{YW16a,
  title={Google's neural machine translation system: Bridging the gap between human and machine translation},
  author={Wu, Yonghui and Schuster, Mike and Chen, Zhifeng and Le, Quoc V and Norouzi, Mohammad and Macherey, Wolfgang and Krikun, Maxim and Cao, Yuan and Gao, Qin and Macherey, Klaus and others},
  journal={arXiv preprint arXiv:1609.08144},
  year={2016}
}

@article{ZLW08a,
	author = {Zhi-Li Wu and Aijun Zhang and Chun-Hung Li and Agus Sudjianto},
	title = {Trace Solution Paths for {SVM}s via Parametric Quadratic
	Programming},
	journal = {KDD Worskshop: Data Mining Using Matrices and Tensors},
	year = {2008},
}

@article{ZLW08a-short,
	author = {Z. Wu and A. Zhang and C. Li and A. Sudjianto},
	title = {Trace Solution Paths for {SVM}s via Parametric Quadratic
	Programming},
	journal = {DMMT},
	year = {2008},
}

@inproceedings{ZW11a,
 author = {Wang, Zhuang and Djuric, Nemanja and Crammer, Koby and Vucetic, Slobodan},
 title = {Trading representability for scalability: adaptive multi-hyperplane machine for nonlinear classification},
 booktitle = {Proceedings of the 17th ACM SIGKDD international conference on Knowledge Discovery and Data Mining},
 year = {2011},
 pages = {24--32}
} 

@inproceedings{HX10a,
	author = {Huosong Xia and Min Tao and Yi Wang},
	title = {Sentiment text classification of customers reviews on the Web based on {SVM}},
	booktitle = {ICNC},
	year = {2010}
}

@article{XL10a,
 title = {Dual Averaging Methods for Regularized Stochastic Learning and Online Optimization},
 author = {Xiao, Lin},
 journal = {Journal of Machine Learning Research},
 volume = {11},
 pages = {2543--2596},
 year = {2010}
}

@inproceedings{LX19a,
author = "Xiao, Lin and Huang, Xin and Chen, Boli and Jing, Liping",
title = "Label-Specific Document Representation for Multi-Label Text Classification",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the Ninth International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)",
year = "2019",
doi = "10.18653/v1/D19-1044",
pages = "466--475",
}

@Inproceedings{LX21a,
title={Does Head Label Help for Long-Tailed Multi-Label Text Classification},
url={https://ojs.aaai.org/index.php/AAAI/article/view/17660},
booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence},
author={Xiao, Lin and Zhang, Xiangliang and Jing, Liping and Huang, Chi and Song, Mingyang},
year={2021},
pages={14103-14111}
}

@inproceedings{WX20a,
author = {Wenyi Xiao and Huan Zhao and Vincent Wenchen Zheng and Yangqiu Song},
title = {Vertex-reinforced Random Walk for Network Embedding},
booktitle = {Proceedings of the 2020 SIAM International Conference on Data Mining (SDM)},
year={2020},
pages = {595--603}
}

@inproceedings{XX19a,
author = {Xie, Xiancheng and Xiong, Yun and Yu, Philip S. and Zhu, Yangyong},
title = {{EHR} Coding with Multi-Scale Feature Attention and Structured Knowledge Graph Propagation},
year = {2019},
booktitle = {Proceedings of the 28th ACM International Conference on Information and Knowledge Management (CIKM)},
doi = {10.1145/3357384.3357897},
pages = {649--658}
}

@inproceedings{YX22a,
  author    = {Xiong, Yuanhao  and
               Chang, Wei-Cheng  and
               Hsieh, Cho-Jui  and
               Finkel, Jenny Rose and
               Yu, Hsiang-Fu  and
               Dhillon, Inderjit},
  title     = {Extreme Zero-Shot Learning for Extreme Text Classification},
  booktitle = {Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL)},
  pages     = {5455--5468},
  year      = {2022}
}

@inproceedings{DX17a,
 author = {Xin, Doris and Mayoraz, Nicolas and Pham, Hubert and Lakshmanan, Karthik and Anderson, John R.},
 title = {Folding: Why Good Models Sometimes Make Spurious Recommendations},
 booktitle = {Proceedings of the Eleventh ACM Conference on Recommender Systems},
 year = {2017},
 pages = {201--209}
}

@inproceedings{DX17a-short,
 author = {Xin, Doris and Mayoraz, Nicolas and Pham, Hubert and Lakshmanan, Karthik and Anderson, John R.},
 title = {Folding: Why Good Models Sometimes Make Spurious Recommendations},
 booktitle = {RecSys},
 year = {2017}
}

@techreport{RX12a,
    Author = {Xin, Reynold Shi and Rosen, Joshua and Zaharia, Matei and Franklin, Michael and Shenker, Scott and Stoica, Ion},
    Title = {Shark: {SQL} and Rich Analytics at Scale},
    Institution = {EECS Department, University of California, Berkeley},
    Year = {2012}
}

@article{ZX19a,
  title={Marc: multi-granular representation learning for networks based on the 3-clique},
  author={Xin, Zhenghua and Chen, Jie and Chen, Guolong and Zhao, Shu},
  journal={IEEE Access},
  volume={7},
  pages={141715--141727},
  year={2019}
}

@inproceedings{CX16a,
author = {Xu, Chang and Tao, Dacheng and Xu, Chao},
title = {Robust Extreme Multi-Label Learning},
year = {2016},
doi = {10.1145/2939672.2939798},
booktitle = {Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)},
pages = {1275--1284}
}

@inproceedings{GX17a,
  title={Convolutional Neural Network using a Threshold Predictor for Multi-label Speech Act Classification}, 
  author={Guanghao Xu and Hyunjung Lee and Myoung-Wan Koo and Jungyun Seo},
  booktitle={Proceedings of IEEE International Conference on Big Data and Smart Computing (BigComp)}, 
  year={2017},
  pages={126--130}
}

@inproceedings{MX13a,
  title={Speedup Matrix Completion with Side Information: Application to
Multi-Label Learning},
  author={Xu, Miao and Jin, Rong and Zhou, Zhi-Hua},
  booktitle={Advances in Neural Information Processing Systems},
  pages={2301--2309},
  year={2013}
}

@inproceedings{WX03a,
 author = {Wei Xu and Xin Liu and Yihong Gong},
 title = {Document clustering based on non-negative matrix factorization},
 booktitle = {Proceedings of the 26th annual international ACM SIGIR conference},
 year = {2003},
 pages = {267--273},
 location = {Toronto, Canada},
 doi = {http://doi.acm.org/10.1145/860435.860485},
 publisher = {ACM Press}
 }

@inproceedings{WX03a-short,
 author = {Wei Xu and Xin Liu and Yihong Gong},
 title = {Document clustering based on non-negative matrix factorization},
 booktitle = {SIGIR},
 year = {2003}
 }

@article{XX21a,
  title={An Information-Explainable Random Walk Based Unsupervised Network Representation Learning Framework on Node Classification Tasks},
  author={Xu, Xin and Lu, Yang and Zhou, Yupeng and Fu, Zhiguo and Fu, Yanjie and Yin, Minghao},
  journal={Mathematics},
  volume={9},
  number={15},
  pages={1767},
  year={2021}
}


@article{YX18a,
    title={Leveraging app usage contexts for app recommendation: a neural approach},
    author={Xu, Yanan and Zhu, Yanmin and Shen, Yanyan and Yu, Jiadi},
    journal={World Wide Web},
    year={2018}
}

@inproceedings{HY03b,
author = {Hiroyasu Yamada and Yuji Matsumoto},
booktitle = {Proceedings of the 8th International Workshop on Parsing
Technologies (IWPT 03)},
title = {Statistical dependency analysis with support vector machines},
year = {2003}
}

@inproceedings{ZY12a,
 author = {Yan, Zhixian and Subbaraju, Vigneshwaran and Chakraborty, Dipanjan and Misra, Archan and Aberer, Karl},
 title = {Energy-Efficient Continuous Activity Recognition on Mobile Phones: An Activity-Adaptive Approach},
 booktitle = {Proceedings of the 2012 16th Annual International Symposium on Wearable Computers (ISWC)},
 year = {2012},
 pages = {17--24}
}

@inproceedings{CY15a,
author = {Yang, Cheng and Liu, Zhiyuan and Zhao, Deli and Sun, Maosong and Chang, Edward Y.},
title = {Network Representation Learning with Rich Text Information},
year = {2015},
pages = {2111--2117},
booktitle = {Proceedings of the Twenty-fourth International Joint Conference on Artificial Intelligence (IJCAI)}
}

@inproceedings{CY17a,
  author    = {Cheng Yang and Maosong Sun and Zhiyuan Liu and Cunchao Tu},
  title     = {Fast Network Embedding Enhancement via High Order Proximity Approximation},
  booktitle = {Proceedings of the Twenty-Sixth International Joint Conference on
               Artificial Intelligence (IJCAI)},
  pages     = {3894--3900},
  year      = {2017}
}

@inproceedings{DY19a,
author = {Yang, Dingqi and Rosso, Paolo and Li, Bin and Cudre-Mauroux, Philippe},
title = {Node{S}ketch: Highly-Efficient Graph Embeddings via Recursive Sketching},
year = {2019},
booktitle = {Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)},
pages = {1162--1172}
}

@Article{JMYang02a,
  author = 	 {Jinn-Moon Yang and Jorng-Tzong Horng and Chih-Jen Lin and Cheng-Yan Kao},
  title = 	 {Optical coating design using the family competition evolutionaty algorithm},
  journal = 	 {Evolutionary Computation},
  volume={9},
  number={4},
  year = 	 {2001},
  pages = {421--444}
}

@inproceedings{JY09a,
 author = {Yang, Jun},
 title = {Toward physical activity diary: motion recognition using simple acceleration features with mobile phones},
 booktitle = {Proceedings of the 1st international workshop on Interactive multimedia for consumer electronics},
 year = {2009},
 pages = {1--10}
}

@Inproceedings{LY16a,
author = {Yang, Liu and Guo, Qi and Song, Yang and Meng, Sha and Shokouhi, Milad and McDonald, Kieran and Croft, W. Bruce},
title = {Modelling User Interest for Zero-query Ranking},
booktitle = {European Conference on Information Retrieval (ECIR)},
year = {2016}
}

@Inproceedings{LY16a-short,
author = {Yang, Liu and Guo, Qi and Song, Yang and Meng, Sha and Shokouhi, Milad and McDonald, Kieran and Croft, W. Bruce},
title = {Modelling User Interest for Zero-query Ranking},
booktitle = {ECIR},
year = {2016}
}

@inproceedings{LY18a,
title={Unbiased offline recommender evaluation for missing-not-at-random implicit feedback},
author={Yang, Longqi and Cui, Yin and Xuan, Yuan and Wang, Chenyang and Belongie, Serge and Estrin, Deborah},
booktitle={Proceedings of the 12th ACM Conference on Recommender Systems},
pages={279--287},
year={2018}
}

@inproceedings{LY18a-short,
title={Unbiased offline recommender evaluation for missing-not-at-random implicit feedback},
author={Yang, Longqi and Cui, Yin and Xuan, Yuan and Wang, Chenyang and Belongie, Serge and Estrin, Deborah},
booktitle={RecSys},
year={2018}
}

@incollection{TY12a,
title = {Nystr\"{o}m Method vs Random Fourier Features: A Theoretical and
Empirical Comparison},
author = {Yang, Tianbao and Li, Yu-feng and Mahdavi, Mehrdad and Jin, Rong
and Zhou, Zhi-Hua},
booktitle = {Advances in Neural Information Processing Systems 25},
pages = {476--484},
year = {2012}
}

@incollection{TY12a-short,
title = {Nystr\"{o}m Method vs Random Fourier Features: A Theoretical and
Empirical Comparison},
author = {Yang, Tianbao and Li, Yu-feng and Mahdavi, Mehrdad and Jin, Rong
and Zhou, Zhi-Hua},
booktitle = {NIPS},
year = {2012}
}


@incollection{TY13b,
title = {Trading Computation for Communication: Distributed Stochastic Dual Coordinate Ascent},
author = {Yang, Tianbao},
booktitle = {Advances in Neural Information Processing Systems 26},
pages = {629--637},
year = {2013}
}

@incollection{TY13b-short,
title = {Trading Computation for Communication: Distributed Stochastic Dual Coordinate Ascent},
author = {Yang, Tianbao},
booktitle = {NIPS},
year = {2013}
}

@article{XY18a,
author = {Yang, Xiaohui and Wan, Rui and Zhang, Haibin and Zeng, Yifu and Liu, Qiao},
title = {Semantical Symbol Mapping Embedding Learning Algorithm for Knowledge Graph},
year = {2018},
journal = {Journal of Computer Research and Development},
volume = {55},
pages = {1773--1784}
}    

@article{YY97a,
  author={Yang, Y. and Pedersen, J.O.},
  title={A comparative study on feature selection in text categorization},
  journal={Proceedings of the Fourteenth International Conference on Machine Learning},
  volume={97},
  year={1997}
}

@article{YY99a,
    author = "Yiming Yang",
    title = "An Evaluation of Statistical Approaches to Text
Categorization",
    journal = "Information Retrieval",
    volume = "1",
    number = "1/2",
    publisher = "Kluwer Academic Publishers",
    pages = "69--90",
    year = "1999"
}

@inproceedings{YY01a,
    author = "Yiming Yang",
    title = "A Study on Thresholding Strategies for Text Categorization",
    booktitle = "Proceedings of the 24th {ACM} International Conference on Research and Development in Information Retrieval",
    publisher = "ACM Press, New York, US",
    address = "New Orleans, US",
    editor = "W. Bruce Croft and David J. Harper and Donald H. Kraft and Justin Zobel",
    pages = "137--145",
    year = "2001"
}
%    url = "citeseer.ist.psu.edu/yang01study.html"

@inproceedings{YY18a,
    title = "Learning Semantic Textual Similarity from Conversations",
    author = "Yang, Yinfei  and
      Yuan, Steve  and
      Cer, Daniel  and
      Kong, Sheng-Yi  and
      Constant, Noah  and
      Pilar, Petr  and
      Ge, Heming  and
      Sung, Yun-Hsuan  and
      Strope, Brian  and
      Kurzweil, Ray",
    booktitle = "Proceedings of The Third Workshop on Representation Learning for {NLP}",
    year = "2018"
}

@inproceedings{YY18a-short,
    title = "Learning Semantic Textual Similarity from Conversations",
    author = "Yang, Yinfei  and
      Yuan, Steve  and
      Cer, Daniel  and
      Kong, Sheng-Yi  and
      Constant, Noah  and
      Pilar, Petr  and
      Ge, Heming  and
      Sung, Yun-Hsuan  and
      Strope, Brian  and
      Kurzweil, Ray",
    booktitle = "{RepL4NLP}",
    year = "2018"
}

@inproceedings{YY10a,
author = {Yang, Yuchieh and Toida, Tatsuo and Hong, Chinming},
title = {Transportations Prediction Using Build-in Triaxial Accelerometer in Cell Phone},
booktitle = {International Conference on Business and Information},
year = {2010}
}

@Article{XY99a,
  author = 	 {X. Yao},
  title = 	 {Evolving artificial neural networks},
  journal = 	 {Proceedings of the IEEE},
  year = 	 {1999},
  volume =	 {87},
  number =	 {9},
  pages =	 {1423--1447}
}

@INPROCEEDINGS{XY21a,
  author={Yao, Xingyu and Shao, Yingxia and Cui, Bin and Chen, Lei},
  booktitle={Proceedings of the 37th IEEE International Conference on Data Engineering (ICDE)}, 
  title={UniNet: Scalable Network Representation Learning with Metropolis-Hastings Sampling}, 
  year={2021},
  pages={516--527}
}

@inproceedings{HY17a,
 author = {Ye, Haishan and Luo, Luo and Zhang, Zhihua},
 title = {Approximate {N}ewton Methods and Their Local Convergence},
 booktitle = {Proceedings of the 34th International Conference on Machine Learning (ICML)},
 year = {2017},
 pages = {3931--3939}
}

@inproceedings{HY17a-short,
 author = {Ye, Haishan and Luo, Luo and Zhang, Zhihua},
 title = {Approximate {N}ewton Methods and Their Local Convergence},
 booktitle = {ICML},
 year = {2017}
}

@article{QY18a,
  title={Using node identifiers and community prior for graph-based classification},
  author={Ye, Qi and Zhu, Changlei and Li, Gang and Liu, Zhimin and Wang, Feng},
  journal={Data Science and Engineering},
  volume={3},
  pages={68--83},
  year={2018}
}

@article{YR01,
  author = 	 {Chen-Hsiang Yeang and Sridhar Ramaswamy and  Pablo Tamayo and  Sayan Mukherjee and
Ryan M. Rifkin and Michael Angelo and Michael Reich and
Eric Lander and Jill Mesirov and Todd Golub
},
  title = 	 {Molecular classification of multiple tumor types},
  journal = 	 {Bioinformatics: Discovery Note},
  year = 	 {2001},
  volume =	 {1},
  number =	 {1},
  pages =	 {1--7}
}

@Article{JY77a,
author  =   {Yellott, Jr., John I.},
title   =   {The relationship between {L}uce's choice axiom, {T}hurstone's
theory of comparative judgment, and the double exponential distribution},
year    =   {1977},
journal =   {Journal of Mathematical Psychology},
volume  =   {15},
number  =   {2},
pages   =   {109--144}
}

@inproceedings{CCY10a,
	title={Unsupervised Feature Selection: Minimize Information Redundancy of Features},
	author={Chun-Chao Yen and Liang-Chieh Chen and Shou-De Lin},
	booktitle={2010 International Conference on Technologies and Applications of Artificial Intelligence},
	pages={247--254},
	year={2010},
	organization={IEEE}
}

@InProceedings{IEY16a,
  title = 	 {{PD}-Sparse : A Primal and Dual Sparse Approach to Extreme Multiclass and Multilabel Classification},
  author = 	 {Yen, Ian En-Hsu and Huang, Xiangru and Ravikumar, Pradeep and Zhong, Kai and Dhillon, Inderjit},
  booktitle = 	 {Proceedings of The 33rd International Conference on Machine Learning (ICML)},
  pages = 	 {3069--3077},
  year = 	 {2016}
}

@inproceedings{IEHY17a,
author = {Yen, Ian En Hsu and Huang, Xiangru and Dai, Wei and Ravikumar, Pradeep and Dhillon, Inderjit and Xing, Eric},
title = {{PPD}sparse: A Parallel Primal-Dual Sparse Method for Extreme Classification},
year = {2017},
booktitle = {Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining},
pages = {545--553}
}

@inproceedings{JNY21a,
	author={Jui-Nan Yen and Chih-Jen Lin},
	title={Limited-memory Common-directions Method With Subsampled Newton Directions for Large-scale Linear Classification},
 booktitle = {Proceedings of the IEEE International Conference on Data Mining (ICDM)},
  url={https://www.csie.ntu.edu.tw/~cjlin/papers/commdir_subsampled/main.pdf}, 
	year={2021}
}

@inproceedings{XY19a,
author = {Yi, Xinyang and Yang, Ji and Hong, Lichan and Cheng, Derek Zhiyuan and Heldt, Lukasz and Kumthekar, Aditee and Zhao, Zhe and Wei, Li and Chi, Ed},
title = {Sampling-Bias-Corrected Neural Modeling for Large Corpus Item Recommendations},
year = {2019},
booktitle = {Proceedings of the 13th ACM Conference on Recommender Systems},
pages = {269–277}
}

@inproceedings{XY19a-short,
author = {Yi, Xinyang and Yang, Ji and Hong, Lichan and Cheng, Derek Zhiyuan and Heldt, Lukasz and Kumthekar, Aditee and Zhao, Zhe and Wei, Li and Chi, Ed},
title = {Sampling-Bias-Corrected Neural Modeling for Large Corpus Item Recommendations},
year = {2019},
booktitle = {RecSys}
}

@article{JY19a,
  title={A semismooth {N}ewton method for support vector classification and regression},
  author={Yin, Juan and Li, Qingna},
  journal={Computational Optimization and Applications},
  volume={73},
  number={2},
  pages={477--508},
  year={2019}
}

@article{JY19a-short,
  title={A semismooth {N}ewton method for support vector classification and regression},
  author={Yin, Juan and Li, Qingna},
  journal={COAP},
  volume={73},
  number={2},
  pages={477--508},
  year={2019}
}

@inproceedings{YY19a,
author = {Yin, Yuan and Wei, Zhewei},
title = {Scalable Graph Embeddings via Sparse Transpose Proximities},
year = {2019},
doi = {10.1145/3292500.3330860},
booktitle = {Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)},
pages = {1429–1437}
}

@inproceedings{NY10a,
 author = {Yoshinaga, Naoki and Kitsuregawa, Masaru},
 title = {Kernel Slicing: Scalable Online Training with Conjunctive Features},
 booktitle = {Proceedings of the 23rd International Conference on
Computational Linguistics},
 year = {2010},
 pages = {1245--1253}
}

@inproceedings{RY19a,
 author = {You, Ronghui and Zhang, Zihan and Wang, Ziye and Dai, Suyang and Mamitsuka, Hiroshi and Zhu, Shanfeng},
 booktitle = {Advances in Neural Information Processing Systems},
 title = {Attention{XML}: Label Tree-based Attention-Aware Deep Model for High-Performance Extreme Multi-Label Text Classification},
 volume = {32},
 year = {2019}
}

@inproceedings{RY19a-short,
 author = {You, Ronghui and Zhang, Zihan and Wang, Ziye and Dai, Suyang and Mamitsuka, Hiroshi and Zhu, Shanfeng},
 booktitle = {NeurIPS},
 title = {Attention{XML}: Label Tree-based Attention-Aware Deep Model for High-Performance Extreme Multi-Label Text Classification},
 year = {2019}
}

@article{DPY89,
author      = {D. P. Young and R.G. Melvin and F. T. Johnson and
                  J. E. Bussoletti and S. S. Samant},
journal     = {SIAM J. Sci. Comput.},
pages       = {1186--1199},
title       = {Application of sparse matrix solvers as effective preconditioners},
volume      = {10},
year        = {1989}
}

@Article{CSY03a,
  author = 	 {Chin-Sheng Yu and Jung-Ying Wang and Jinn-Moon Yang and Ping-Chiang Lyu and Chih-Jen Lin and Jen-Kang Hwang},
  title = 	 {Fine-grained protein fold assignment by support vector machines using generalize $n$peptide coding schemes and jury voting from multiple-parameter sets},
  journal = 	 {Proteins},
  year = 	 {2003},
  volume =	 {50},
  pages =	 {531--536}
}


@Article{CSY04a,
  author = 	 {Chin-Sheng Yu and Chih-Jen Lin and Jen-Kang Hwang},
  title = 	 {Predicting subcellular localization of proteins for {G}ram-negative bacteria by support vector machines based on $n$-peptide compositions},
  journal = 	 {Protein Science},
  year = 	 {2004},
  volume =	 {13},
  pages =	 {1402--1406}
}

@Article{HFY10a,
author ={Hsiang-Fu Yu and Fang-Lan Huang and Chih-Jen Lin},
title ={Dual Coordinate Descent Methods for Logistic Regression and Maximum Entropy Models},
year = {2011},
journal = 	 {Machine Learning},
url ={http://www.csie.ntu.edu.tw/~cjlin/papers/maxent_dual.pdf},
  pages={41--75},
  month =	 {October},
  number =	 {1-2},
  volume={85}
}

@Article{HFY10a-short,
author ={Hsiang-Fu Yu and Fang-Lan Huang and Chih-Jen Lin},
title ={Dual Coordinate Descent Methods for Logistic Regression and Maximum Entropy Models},
year = {2011},
journal = 	 {MLJ},
  pages={41--75},
  volume={85}
}

@inproceedings{HFY10b,
  author    = {Hsiang-Fu Yu and Cho-Jui Hsieh and Kai-Wei Chang and Chih-Jen Lin},
  title     = {Large linear classification when data cannot fit in memory},
  booktitle = {Proceedings of the Sixteenth ACM SIGKDD International
Conference on Knowledge Discovery and Data Mining},
  year      = {2010},
  pages     = {833--842},
  url={http://www.csie.ntu.edu.tw/~cjlin/papers/kdd_disk_decomposition.pdf}
}

@inproceedings{HFY10b-short,
  author    = {Hsiang-Fu Yu and Cho-Jui Hsieh and Kai-Wei Chang and
Chih-Jen Lin},
  title     = {Large linear classification when data cannot fit in memory},
 booktitle = {ACM KDD},
  year      = {2010},
}


@InProceedings{HFY10c,
  author = 	 {Hsiang-Fu Yu and Hung-Yi Lo and 
Hsun-Ping Hsieh and  Jing-Kai Lou and  Todd G. McKenzie and 
Jung-Wei Chou and Po-Han Chung and Chia-Hua Ho and  
Chun-Fu Chang and Yin-Hsuan Wei and Jui-Yu Weng and En-Syu Yan and
Che-Wei Chang and Tsung-Ting Kuo and Yi-Chen Lo and 
Po Tzu Chang and Chieh Po and Chien-Yuan Wang and  
Yi-Hung Huang and Chen-Wei Hung and Yu-Xun Ruan and 
Yu-Shi Lin and Shou-De Lin and Hsuan-Tien Lin and Chih-Jen Lin},
  title = 	 {Feature Engineering and Classifier Ensemble for {KDD} {C}up 2010},
  booktitle = 	 {JMLR Workshop and Conference Proceedings},
  year = 	 {2011},
  url = {http://www.csie.ntu.edu.tw/~cjlin/courses/dmcase2010/kdd2010ntu.pdf},
  OPTkey = 	 {},
  OPTtype = 	 {},
  OPTnumber = 	 {},
  OPTaddress = 	 {},
  OPTmonth = 	 {},
  note =	 {To appear},
  OPTannote = 	 {}
}

@article{HFY11a,
  author    = {Hsiang-Fu Yu and Cho-Jui Hsieh and Kai-Wei Chang and Chih-Jen Lin},
  title     = {Large linear classification when data cannot fit in memory},
  journal = {ACM Transactions on Knowledge Discovery from Data},
  year      = {2012},
  pages = {23:1--23:23},
  month =	 {February},
  number =	 {4},
  volume={5},
  url={http://www.csie.ntu.edu.tw/~cjlin/papers/kdd_disk_decomposition.pdf}
}

@article{HFY11a-short,
  author    = {Hsiang-Fu Yu and Cho-Jui Hsieh and Kai-Wei Chang and Chih-Jen Lin},
  title     = {Large linear classification when data cannot fit in memory},
  journal = {ACM TKDD},
  year      = {2012},
  volume={5}
}


@TechReport{HFY12b,
author = {Hsiang-Fu Yu and Chia-Hua Ho and Prakash Arunachalam and Manas Somaiya
  and Chih-Jen Lin}, 
title = {Product Title Classification versus Text Classification},
year = {2012},
url={http://www.csie.ntu.edu.tw/~cjlin/papers/title.pdf}
}

@inproceedings{HFY12c,
  author    = {Hsiang-Fu Yu and
               Cho-Jui Hsieh and
               Si Si and
               Inderjit S. Dhillon},
  title     = {Scalable Coordinate Descent Approaches to Parallel Matrix
               Factorization for Recommender Systems},
  booktitle = {Proceedings of the IEEE International Conference on Data Mining},
  year      = {2012},
  pages     = {765-774}
}

@inproceedings{HFY12c-short,
  author    = {Hsiang-Fu Yu and
               Cho-Jui Hsieh and
               Si Si and
               Inderjit S. Dhillon},
  title     = {Scalable Coordinate Descent Approaches to Parallel Matrix
               Factorization for Recommender Systems},
  booktitle = {ICDM},
  year      = {2012},
}

@article{HFY14a,
  author = {Hsiang-Fu Yu and Cho-Jui Hsieh and Si Si and Inderjit S. Dhillon},
  title = {Parallel Matrix Factorization for Recommender Systems},
  journal = {Knowledge and Information Systems},
  volume = {41},
  number = {3},
  pages = {793--819},
  year = {2014},
}

@article{HFY14a-short,
  author = {Hsiang-Fu Yu and Cho-Jui Hsieh and Si Si and Inderjit S. Dhillon},
  title = {Parallel Matrix Factorization for Recommender Systems},
  journal = {KAIS},
  volume = {41},
  pages = {793--819},
  year = {2014},
}

@InProceedings{HFY14b,
	author       = {Hsiang-Fu Yu and Prateek Jain and Purushottam Kar and Inderjit S. Dhillon},
	title        = {Large-scale Multi-label Learning with Missing Labels},
	booktitle    = {Proceedings of the Thirty First International Conference on Machine Learning (ICML)},
	pages        = {593--601},
	year         = {2014}
}

@InProceedings{HFY14b-short,
	author       = {Hsiang-Fu Yu and Prateek Jain and Purushottam Kar and Inderjit S. Dhillon},
	title        = {Large-scale Multi-label Learning with Missing Labels},
	booktitle    = {ICML},
	year         = {2014}
}


@InProceedings{HFY16a,
  author = {Hsiang-Fu Yu and Mikhail Bilenko and Chih-Jen Lin},
  title = {Selection of Negative Samples for One-class Matrix
Factorization},
  booktitle =	 {Proceedings of SIAM International Conference on Data Mining (SDM)},
  year =	 {2017},
  url={http://www.csie.ntu.edu.tw/~cjlin/papers/one-class-mf/biased-mf-sdm-with-supp.pdf}
}

@InProceedings{HFY16a-short,
  author = {Hsiang-Fu Yu and Mikhail Bilenko and Chih-Jen Lin},
  title = {Selection of Negative Samples for One-class Matrix
Factorization},
  booktitle =	 {SDM},
  year =	 {2017}
}

@InProceedings{HFY17a,
  author = {Hsiang-Fu Yu and Hsin-Yuan Huang and Inderjit S. Dihillon and Chih-Jen Lin},
  title = {A Unified Algorithm for One-class Structured Matrix Factorization with Side Information},
  booktitle =	 {Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence (AAAI)},
  year =	 {2017},
  url={http://www.csie.ntu.edu.tw/~cjlin/papers/ocmf-side/biased-leml-aaai-with-supp.pdf}
}

@InProceedings{HFY17a-short,
  author = {Hsiang-Fu Yu and Hsin-Yuan Huang and Inderjit S. Dihillon and Chih-Jen Lin},
  title = {A Unified Algorithm for One-class Structured Matrix Factorization with Side Information},
  booktitle =	 {AAAI},
  year =	 {2017}
}

@article{HFY22a,
  author  = {Hsiang-Fu Yu and Kai Zhong and Jiong Zhang and Wei-Cheng Chang and Inderjit S. Dhillon},
  title   = {{PECOS}: Prediction for Enormous and Correlated Output Spaces},
  journal = {Journal of Machine Learning Research},
  year    = {2022},
  volume  = {23},
  number  = {98},
  pages   = {1--32}
}

@inproceedings{HY03a,
 author = {Hwanjo Yu and Jiong Yang and Jiawei Han},
 title = {Classifying large data sets using {SVM}s with hierarchical clusters},
 booktitle = {Proceedings of the Ninth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining},
 year = {2003},
 isbn = {1-58113-737-0},
 pages = {306--315},
 location = {Washington, D.C.},
 doi = {http://doi.acm.org/10.1145/956750.956786},
 publisher = {ACM Press},
 address = {New York, NY, USA},
 }


@inproceedings{HY03a-short,
 author = {Hwanjo Yu and Jiong Yang and Jiawei Han},
 title = {Classifying large data sets using {SVM}s with hierarchical clusters},
 booktitle = {ACM KDD},
 year = {2003}
 }



@article{HY12a,
 author={Yu, Hwanjo and Kim, Jinha and Kim, Youngdae and Hwang, Seungwon and Lee, Young Ho},
 title={An Efficient Method for Learning Nonlinear Ranking {SVM} Functions},
 journal={Information Sciences},
 volume={209},
 pages={37-48},
 year={2012},
 publisher={Elsevier}
}

@Article{JY10a,
author = {Jin Yu and S.V.N. Vishwanathan and Simon Gunter and Nicol N.
Schraudolph},
title = {A Quasi-{N}ewton Approach to Nonsmooth Convex Optimization
Problems in Machine Learning},
  journal = 	 {Journal of Machine Learning Research},
  year =     {2010},
  pages={1--57},
  volume={11}
}

@techreport{MCY13a,
author={Meng-Chieh Yu and Tong Yu and Chih-Jen Lin and Edward Y. Chang},
institution={Studio Engineering, HTC},
title={Low Power and Low Cost Sensor Hub for Transportation-mode Detection},
url = {http://www.csie.ntu.edu.tw/~cjlin/papers/transportation-mode/transportation.pdf},
year={2013}
}


@article{MCY14a,
 author = {Meng-Chieh Yu and Tong Yu and Shao-Chen Wang and Chih-Jen Lin and Edward Y. Chang},
 title = {Big Data Small Footprint: The Design of A Low-Power Classifier for Detecting Transportation Modes},
 journal = {Proceedings of the VLDB Endowment},
 volume = {7},
 year = {2014},
 pages = {1429--1440}
} 


@incollection{KY08a,
title = {Nonlinear Learning using Local Coordinate Coding},
author = {Yu, Kai and Zhang, Tong and Yihong Gong},
booktitle = {Advances in Neural Information Processing Systems 22},
editor = {Y. Bengio and D. Schuurmans and J. D. Lafferty and C. K. I. Williams and A. Culotta},
pages = {2223--2231},
year = {2009}
}

@techreport{TY13a,
author={Tong Yu and Daniel Wang and Meng-Chieh Yu and Chih-Jen Lin and Edward Y. Chang},
institution={Studio Engineering, HTC},
title={Careful Use of Machine Learning Methods Is Needed for Mobile Applications: A Case Study on Transportation-mode Detection},
year={2013},
url = {http://www.csie.ntu.edu.tw/~cjlin/papers/transportation-mode/casestudy.pdf}
}

@inproceedings{ZQY14a,
 author = {Yu, Zhi-Qin and Shi, Xing-Jian and Yan, Ling and Li, Wu-Jun},
 title = {Distributed Stochastic {ADMM} for Matrix Factorization},
 booktitle = {Proceedings of the 23rd ACM International Conference on Conference on Information and Knowledge Management (CIKM)},
 year = {2014}
} 

@inproceedings{ZQY14a-short,
author = {Yu, Zhi-Qin and Shi, Xing-Jian and Yan, Ling and Li, Wu-Jun},
title = {Distributed Stochastic {ADMM} for Matrix Factorization},
booktitle = {CIKM},
year = {2014}
} 

@techreport{BY18a,
  author = {Yuan, Bo-Wen and Su, Chuan-Yao and Gong, Ben-Wei and Liu, Zhirong and Dong, Zhenhua and Lin, Chih-Jen},
  title = {Trending Query Recommendation by One-class Matrix Factorization},
  institution = {National Taiwan University},
  year={2018}
}

@techreport{BY19a,
author = {Yuan, Bowen and Yang, Meng-Yuan and Hsia, Jui-Yang and Zhu, Hong and Liu, Zhirong and Dong, Zhenhua and Lin, Chih-Jen},
title = {One-class Field-aware Factorization Machines for Recommender Systems with Implicit Feedbacks},
institution = {National Taiwan University},
year = {2019},
url = {http://www.csie.ntu.edu.tw/~cjlin/papers/ocffm/imp_ffm.pdf},  
}


@techreport{BY19a-short,
author = {Yuan, Bowen and Yang, Meng-Yuan and Hsia, Jui-Yang and Zhu, Hong and Liu, Zhirong and Dong, Zhenhua and Lin, Chih-Jen},
title = {One-class Field-aware Factorization Machines for Recommender Systems with Implicit Feedbacks},
institution = {National Taiwan Univ.},
year = {2019}
}

@InProceedings{BY19b,
  author = 	 {Bowen Yuan and Jui-Yang Hsia and Meng-Yuan Yang and Hong Zhu and Chihyao Chang and Zhenhua Dong and Chih-Jen Lin},
  title = 	 {Improving {A}d Click Prediction by Considering Non-displayed Events},
  url = {http://www.csie.ntu.edu.tw/~cjlin/papers/occtr/ctr_oc.pdf},  
  OPTcrossref =  {},
  OPTkey = 	 {},
  booktitle = {Proceedings of the 28th ACM International Conference on Conference on Information and Knowledge Management (CIKM)},
  year =	 {2019},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTpages = 	 {},
  OPTmonth = 	 {},
  OPTaddress = 	 {},
  OPTorganization = {},
  OPTpublisher = {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@InProceedings{BY19b-short,
  author = 	 {Bowen Yuan and Jui-Yang Hsia and Meng-Yuan Yang and Hong Zhu and Chihyao Chang and Zhenhua Dong and Chih-Jen Lin},
  title = 	 {Improving {A}d Click Prediction by Considering Non-displayed Events},
  booktitle = {CIKM},
  year =	 {2019}
}


@InProceedings{BY20a,
  author = 	 {Bowen Yuan and Yaxu Liu and Jui-Yang Hsia and Zhenhua Dong and Chih-Jen Lin},
  title = 	 {Unbiased Ad click prediction for position-aware advertising systems},
  url = {http://www.csie.ntu.edu.tw/~cjlin/papers/debiases/debiases.pdf},  
  OPTcrossref =  {},
  OPTkey = 	 {},
booktitle={Proceedings of the 14th ACM Conference on Recommender Systems},  
  year =	 {2020},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTpages = 	 {},
  OPTmonth = 	 {},
  OPTaddress = 	 {},
  OPTorganization = {},
  OPTpublisher = {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@inproceedings{BY21a,
  author = {Bowen Yuan and Yu-Sheng Li and Pengrui Quan and Chih-Jen Lin},
  title = {Efficient optimization methods for extreme similarity learning with nonlinear embeddings},
  booktitle = {Proceedings of the ACM SIGKDD International
Conference on Knowledge Discovery and Data Mining (KDD)},
  year = {2021},
  url = {http://www.csie.ntu.edu.tw/~cjlin/papers/similarity_learning/pq.pdf}
}


@inproceedings{FY18a,
  title={f{BGD}: Learning embeddings from positive unlabeled data with {BGD}},
  author={Yuan, Fajie and Xin, Xin and He, Xiangnan and Guo, Guibing and Zhang, Weinan and Tat-Seng, Chua and Jose, Joemon M.},
  booktitle = {Proceedings of the Thirty-Fourth Conference on
		Uncertainty in Artificial Intelligence (UAI)},
  year={2018}
}

@inproceedings{FY18a-short,
  title={f{BGD}: Learning embeddings from positive unlabeled data with {BGD}},
  author={Yuan, Fajie and Xin, Xin and He, Xiangnan and Guo, Guibing and Zhang, Weinan and Tat-Seng, Chua and Jose, Joemon M.},
  booktitle = {UAI},
  year={2018}
}

@Article{GXY09a,
  author = {Guo-Xun Yuan and Kai-Wei Chang and Cho-Jui Hsieh and Chih-Jen Lin},
  title = {A Comparison of Optimization Methods 
and software for Large-scale L1-regularized Linear Classification},
  journal= {Journal of Machine Learning Research},
  url = {http://www.csie.ntu.edu.tw/~cjlin/papers/l1.pdf},
  year = {2010},
  volume =	 {11},
  OPTnumber = 	 {},
  pages =	 {3183--3234},

}

@Article{GXY09a-short,
  author = {Guo-Xun Yuan and Kai-Wei Chang and Cho-Jui Hsieh and Chih-Jen Lin},
  title = {A Comparison of Optimization Methods 
and software for Large-scale L1-regularized Linear Classification},
  journal= {JMLR},
  url = {http://www.csie.ntu.edu.tw/~cjlin/papers/l1.pdf},
  year = {2010},
  volume =	 {11},
  pages =	 {3183--3234}
}

@article{GXY11a,
  author = {Guo-Xun Yuan and Chia-Hua Ho and Chih-Jen Lin},
  title = {An Improved {GLMNET} for L1-regularized Logistic Regression},
  journal = {Journal of Machine Learning Research},
  volume = {13},
  year = {2012},
  pages = {1999--2030},
  url={http://www.csie.ntu.edu.tw/~cjlin/papers/l1_glmnet/long-glmnet.pdf}
}

@article{GXY11a-short,
  author = {Guo-Xun Yuan and Chia-Hua Ho and Chih-Jen Lin},
  title = {An Improved {GLMNET} for L1-regularized Logistic Regression},
  journal = {JMLR},
  volume = {13},
  year = {2012}
}

@inproceedings{GXY11b,
  author = {Guo-Xun Yuan and Chia-Hua Ho and Chih-Jen Lin},
  title = {An Improved {GLMNET} for L1-regularized Logistic Regression},
  booktitle = {Proceedings of the Seventeenth ACM SIGKDD International
Conference on Knowledge Discovery and Data Mining},
  year = {2011},
  pages =	 {33--41}
}


@article{GXY11c,
  author = {Guo-Xun Yuan and Chia-Hua Ho and Chih-Jen Lin},
  title = {Recent advances of large-scale linear classification},
  url = {http://www.csie.ntu.edu.tw/~cjlin/papers/survey-linear.pdf},
  journal = {Proceedings of the IEEE},
  year = {2012},
  volume =	 {100},
  number =	 {9},
  pages =	 {2584--2603}
}

@article{GXY11c-short,
  author = {Guo-Xun Yuan and Chia-Hua Ho and Chih-Jen Lin},
  title = {Recent advances of large-scale linear classification},
  journal = {PIEEE},
  year = {2012},
  volume =	 {100},
  pages =	 {2584--2603}
}

@INPROCEEDINGS{MY19a,
author={Yuan, Mengqi and Xu, Jinke and Li, Zhongnian},
booktitle={Proceedings of IEEE Second International Conference on Artificial Intelligence and Knowledge Engineering (AIKE)},
title={Long Tail Multi-label Learning},
year={2019},
pages={28--31}
}

@inproceedings{SY14a,
 author = {Yuan, Shuai and Wang, Jun and Chen, Bowei and Mason, Peter and Seljan, Sam},
 title = {An Empirical Study of Reserve Price Optimisation in Real-time Bidding},
 booktitle = {Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)},
 year = {2014},
 pages = {1897--1906}
} 

@article{XY20a,
  title={Graph embedding on biomedical networks: methods, applications and evaluations},
  author={Yue, Xiang and Wang, Zhen and Huang, Jingong and Parthasarathy, Srinivasan and Moosavinasab, Soheil and Huang, Yungui and Lin, Simon M and Zhang, Wen and Zhang, Ping and Sun, Huan},
  journal={Bioinformatics},
  volume={36},
  pages={1241--1251},
  year={2020}
}

@inproceedings{HY13a,
author = "Hyokun Yun AND Hsiang-Fu Yu AND Cho-Jui Hsieh AND S.V.N. Vishwanathan AND Inderjit S. Dhillon",
title = "NOMAD: Non-locking, stochastic Multi-machine algorithm for Asynchronous and Decentralized matrix completion",
booktitle = "International Conference on Very Large Data Bases (VLDB)",
year = "2014"
}

@inproceedings{HY13a-short,
author = "Hyokun Yun AND Hsiang-Fu Yu AND Cho-Jui Hsieh AND S.V.N. Vishwanathan AND Inderjit S. Dhillon",
title = "NOMAD: Non-locking, stochastic Multi-machine algorithm for Asynchronous and Decentralized matrix completion",
booktitle = "VLDB",
year = "2014"
}

@Article{SY09a,
  author = {Sangwoon Yun and Kim-Chuan Toh},
  title = {A Coordinate Gradient Descent Method for L1-regularized
Convex Minimization},
  journal = {Computational Optimizations and Applications},
  volume =	 {48},
  number =	 {2},
  pages =	 {273--307},
  year = {2011}
}

@article{SY09a-short,
  title={A coordinate gradient descent method for L1-regularized
convex minimization},
  author={Yun, Sangwoon and Toh, Kim-Chuan},
  journal={Comput. Opt. App.},
  volume={48},
  pages={273--307},
  year={2011}
}


@Incollection{BZ01a,
  author    = "Bianca Zadrozny",
  original  = "orig/AA63.ps",  
  title     = "Reducing multiclass to binary by coupling probability estimates",
  booktitle = "Advances in Neural Information Processing Systems 14",
  editor    = "T. G. Dietterich and S. Becker and Z. Ghahramani",
  publisher = "MIT Press",
  address   = "Cambridge, MA",
  pages     = "1041--1048",
  year      = "2002",
}

@InProceedings{BZ02a,
  author = 	 {Bianca Zadrozny and C. Elkan},
  title = 	 {Transforming classifier scores into accurate
multiclass probability estimates},
  booktitle = 	 {Proceedings of the Eighth
International Conference on Knowledge Discovery and Data Mining},
  year =	 {2002}
}


@inproceedings{MZ10b,
 author = {Zaharia, Matei and Chowdhury, Mosharaf and Franklin, Michael J. and Shenker, Scott and Stoica, Ion},
 title = {Spark: cluster computing with working sets},
 booktitle = {Proceedings of the 2nd USENIX conference on Hot topics in cloud computing},
 year = {2010}
} 

@inproceedings{MZ12a,
		title={Resilient distributed datasets: A fault-tolerant abstraction for in-memory cluster computing},
		author={Zaharia, Matei and Chowdhury, Mosharaf and Das, Tathagata and Dave, Ankur and Ma, Justin and McCauley, Murphy and Franklin, Michael J and 
				Shenker, Scott and Stoica, Ion},
		booktitle={Proceedings of the 9th USENIX conference on Networked Systems Design and Implementation},
		year={2012}
}

@INPROCEEDINGS{MZB13a, 
    author={Mauricio Zambrano-Bigiarini and Maurice Clerc and Rodrigo Rojas-Mujica},
    booktitle={IEEE Congress on Evolutionary Computation}, 
    title={Standard Particle Swarm Optimisation 2011 at CEC-2013: A baseline for future PSO improvements}, 
    year={2013}, 
    volume={}, 
    number={}, 
    pages={2337-2344}
}

@Article{LZ06a,
  author = 	 {L. Zanni and T. Serafini and G. Zanghirati},
  title = 	 {Parallel Software for Training Large Scale Support Vector Machines on Multiprocessor Systems},
  journal = 	 {Journal of Machine Learning Research},
  year = 	 {2006},
  OPTkey = 	 {},
  volume =	 {7},
  OPTnumber = 	 {},
  pages =	 {1467--1492},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@article{RZ08a,
  title={Fast nonnegative matrix factorization algorithms using projected
gradient approaches for large-scale problems},
  author={Rafal Zdunek and Andrzej Cichocki},
  journal={Computational Intelligence and Neuroscience},
  pages={1--13},
  volume={2008},
  year={2008}
}

@article{MDZ12a,
author = {Zeiler, Matthew D.},
journal = {CoRR},
title = {{ADADELTA}: An Adaptive Learning Rate Method},
year = {2012}
}

@inproceedings{MDZ14a,
  title={Visualizing and understanding convolutional networks},
  author={Zeiler, Matthew D. and Fergus, Rob},
  booktitle={Proceedings of European Conference on Computer Vision},
  pages={818--833},
  year={2014}
}


@Article{EZ29a,
  author = 	 {Zermelo, Ernst},
  title = 	 {{D}ie {B}erechnung der {T}urnier-{E}rgebnisse als ein {M}aximumproblem der 
 {W}ahrscheinlichkeitsrechnung},
  journal = 	 {Mathematische Zeitschrift},
  year = 	 {1929},
  volume =	 {29},
  pages =	 {436--460}
}



@InProceedings{CZ12a,
  author = 	 {Caoxie Zhang and Honglak Lee and Kang G. Shin},
  title = 	 {Efficient distributed linear classification algorithms via the alternating direction method of multipliers},
  OPTcrossref =  {},
  OPTkey = 	 {},
  booktitle =	 {Proceedings of the 15th International Conference on Artificial Intelligence and Statistics},
  OPTpages = 	 {},
  year =	 {2012},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTaddress = 	 {},
  OPTmonth = 	 {},
  OPTorganization = {},
  OPTpublisher = {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@InProceedings{CZ12a-short,
  author = 	 {Caoxie Zhang and Honglak Lee and Kang G. Shin},
  title = 	 {Efficient distributed linear classification algorithms via the alternating direction method of multipliers},
  booktitle =	 {AISTATS},
  year =	 {2012}
}

@inproceedings{CZ19a,
author = {Zhang, Chuxu and Song, Dongjin and Huang, Chao and Swami, Ananthram and Chawla, Nitesh V.},
title = {Heterogeneous Graph Neural Network},
year = {2019},
booktitle = {Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)},
pages = {793--803}
}

@InCollection{DZ03a,
  author = 	 {Dell Zhang and Wee Sun Lee},
  title = 	 {Question Classification using Support Vector Machines},
 booktitle = {Proceedings of the 26th annual international ACM SIGIR conference on Research and development in informaion retrieval},
 pages = {26--32},
  OPTcrossref =  {},
  OPTkey = 	 {},
  OPTpublisher = {},
  year =	 {2003},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTtype = 	 {},
  OPTchapter = 	 {},
  OPTaddress = 	 {},
  OPTedition = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@InProceedings{DZ03a-short,
	author = {Dell Zhang and Wee Sun Lee},
	title = {Question classification using support vector machines},
	booktitle = {SIGIR},
	year = {2003},
	pages = {26--32}
}

@article{HZ19a,
  title={{MANELA}: A Multi-Agent Algorithm for Learning Network Embeddings},
  author={Zhang, Han and Xu, Hong},
  journal={arXiv preprint arXiv:1912.00303},
  year={2019}
}

@inproceedings{HZ16b,
  title={Discrete collaborative filtering},
  author={Zhang, Hanwang and Shen, Fumin and Liu, Wei and He, Xiangnan and Luan, Huanbo and Chua, Tat-Seng},
  booktitle={Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval},
  pages={325--334},
  year={2016}
}

@InProceedings{HZ16a,
  author={Zhang, Huan and Hsieh, Cho-Jui},
  title={Fixing the Convergence Problems in Parallel Asynchronous Dual Coordinate Descent},
  year={2016},
 booktitle = {Proceedings of the IEEE International Conference
on Data Mining (ICDM)},
  pages={619--628}
}


@InProceedings{HZ16a-short,
  author={Zhang, Huan and Hsieh, Cho-Jui},
  title={Fixing the Convergence Problems in Parallel Asynchronous Dual Coordinate Descent},
  year={2016},
 booktitle = {ICDM}
}

@misc{HZ17a,
  author    = {Huishuai Zhang and
               Caiming Xiong and
               James Bradbury and
               Richard Socher},
  title     = {Block-diagonal {H}essian-free Optimization for Training Neural Networks},
  year      = {2017},
  note={arXiv preprint arXiv:1712.07296}
}


@inproceedings{JZ03a,
  author    = {Jian Zhang and Rong Jin and Yiming Yang and Alex G. Hauptmann},
  title     = {Modified logistic regression: an approximation to {SVM} and its applications
in large-scale text categorization},
  booktitle = {Proceedings of the Twentieth International Conference on
               Machine Learning (ICML)},
  year      = {2003},
  pages     = {}
}

@inproceedings{JZ03a-short,
  author    = {Jian Zhang and Rong Jin and Yiming Yang and Alex G. Hauptmann},
  title     = {Modified logistic regression: an approximation to {SVM} and its applications
in large-scale text categorization},
  booktitle = {ICML},
  year      = {2003},
  pages     = {}
}

@inproceedings{JZ22a,

  title={{ADAM}: An Attentional Data Augmentation Method for Extreme Multi-label Text Classification},
  author={Zhang, Jiaxin and Liu, Jie and Chen, Shaowei and Lin, Shaoxin and Wang, Bingquan and Wang, Shanpeng},
  booktitle={Proceedings of the Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD)},
  pages={131--142},
  year={2022}
}

@misc{JZ18a,
      title={Spectral Network Embedding: A Fast and Scalable Method via Sparsity}, 
      author={Jie Zhang and Yan Wang and Jie Tang and Ming Ding},
      year={2018},
      eprint={1806.02623},
      archivePrefix={arXiv},
      primaryClass={cs.SI}
}

@inproceedings{JZ19a,
  title     = {Pro{NE}: Fast and Scalable Network Representation Learning},
  author    = {Zhang, Jie and Dong, Yuxiao and Wang, Yan and Tang, Jie and Ding, Ming},
  booktitle = {Proceedings of the Twenty-Eighth International Joint Conference on
               Artificial Intelligence (IJCAI)},
  pages     = {4278--4284},
  year      = {2019}
}

@INPROCEEDINGS{JZ19b,
  author={Zhang, Jie and Wang, Yan and Tang, Jie},
  booktitle={Proceedings of IEEE Fourth International Conference on Data Science in Cyberspace (DSC)}, 
  title={A Fast Network Embedding Approach with Preserving Hierarchical Proximities}, 
  year={2019},
  pages={142--149}
}

@inproceedings{JZ21b,
 author = {Zhang, Jiong and Chang, Wei-Cheng and Yu, Hsiang-Fu and Dhillon, Inderjit},
 booktitle = {Advances in Neural Information Processing Systems},
 editor = {M. Ranzato and A. Beygelzimer and Y. Dauphin and P.S. Liang and J. Wortman Vaughan},
 pages = {7267--7280},
 title = {Fast Multi-Resolution Transformer Fine-tuning for Extreme Multi-label Text Classification},
 volume = {34},
 year = {2021}
}

@inproceedings{JZ23a,
  title={Build Faster with Less: A Journey to Accelerate Sparse Model Building for Semantic Matching in Product Search},
  author={Zhang, Jiong and Wang, Yau-Shian and Chang, Wei-Cheng and Li, Wei and Jiang, Jyun-Yu and Hsieh, Cho-Jui and Yu, Hsiang-Fu},
  booktitle={Proceedings of the 32nd ACM International Conference on Information and Knowledge Management},
  pages={4960--4966},
  year={2023}
}

@inproceedings{KZ08a,
  title = {Improved {Nystr\"{o}m} Low-Rank Approximation and Error Analysis},
  author = {Kai Zhang and Ivor W. Tsang and James T. Kwok},
  booktitle = {Proceedings of the Twenty Fifth International Conference on
               Machine Learning (ICML)},
  year = {2008},
} 

@inproceedings{KZ08a-short,
  title = {Improved {Nystr\"{o}m} Low-Rank Approximation and Error Analysis},
  author = {Kai Zhang and Ivor W. Tsang and James T. Kwok},
  booktitle = {ICML},
  year = {2008},
} 

@inproceedings{KZ12a, 
    Title = {Scaling up Kernel {SVM} on Limited Resources: A Low-rank Linearization Approach}, 
    Author = {Kai Zhang and Liang Lan and Zhuang Wang and Fabian Moerchen}, 
    Pages = {1425-1434}, 
    Year = {2012},
  booktitle =    {Proceedings of the 15th International Conference Artificial Intelligence and Statistics (AISTATS)},
}

@inproceedings{KZ12a-short, 
    Title = {Scaling up Kernel {SVM} on Limited Resources: A Low-rank Linearization Approach}, 
    Author = {Kai Zhang and Liang Lan and Zhuang Wang and Fabian Moerchen}, 
    Booktitle = {AISTATS},
    year = {2012}
}

@article{LZ20a,
      title={{EPINE}: Enhanced Proximity Information Network Embedding}, 
      author={Luoyi Zhang and Ming Xu},
      year={2020},
      journal={arXiv preprint arXiv:2003.02689}
}

@InProceedings{MLZ05a,
  author = 	 {M.-L. Zhang and Z.-H. Zhou},
  title = 	 {A k-nearest neighbor based algorithm for multi-label classification},
  booktitle = 	 {Proceedings of the 1st IEEE International Conference on Granular Computing},
  OPTcrossref =  {},
  OPTkey = 	 {},
  OPTpages = 	 {},
  year =	 {2005},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTaddress = 	 {},
  OPTmonth = 	 {},
  OPTorganization = {},
  OPTpublisher = {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

  @article{MLZ06a,
  title={Multilabel Neural Networks with Applications to Functional Genomics and Text Categorization},
  author={Zhang, Min-Ling and Zhou, Zhi-Hua},
  journal={IEEE Transactions on Knowledge and Data Engineering},
  volume={18},
  number={10},
  pages={1338--1351},
  year={2006}
}

@article{MLZ07a,
  title={{ML-KNN}: A lazy learning approach to multi-label learning},
  author={Zhang, Min-Ling and Zhou, Zhi-Hua},
  journal={Pattern Recognition},
  volume={40},
  number={7},
  pages={2038--2048},
  year={2007},
  publisher={Elsevier}
}

@ARTICLE{MLZ14a,
  author={Zhang, Min-Ling and Zhou, Zhi-Hua},
  journal={IEEE Transactions on Knowledge and Data Engineering}, 
  title={A Review on Multi-Label Learning Algorithms}, 
  year={2014},
  volume={26},
  number={8},
  pages={1819--1837},
  doi={10.1109/TKDE.2013.39}
}

@article{SZ05a,
        author={S. Zhang and W. Wang and Ford, J. and Makedon, F. and Pearlman, J.},
        title={Using {S}ingular {V}alue {D}ecomposition approximation for collaborative filtering},
        journal={Seventh IEEE International Conference on E-Commerce Technology, 2005. CEC 2005.},
        year={2005},
        month={July},
        volume={},
        number={},
        pages={257--264},
        keywords={ information filters, optimisation, singular value decomposition collaborative filtering, distributed recommendation systems, expectation-maximization procedure, log-likelihood maximization, singular value decomposition approximation},
        doi={10.1109/ICECT.2005.102},
        ISSN={1530-1354},
}

@inproceedings{TZ21a,
title={Revisiting Few-sample {BERT} Fine-tuning},
author={Tianyi Zhang and Felix Wu and Arzoo Katiyar and Kilian Q. Weinberger and Yoav Artzi},
booktitle={Proceedings of International Conference on Learning Representations},
year={2021}
}

@inproceedings{TZ01,
  author =	{Tong Zhang},
  title =	{A Leave-one-out Cross Validation Bound for Kernel Methods with Applications in Learning},
    booktitle = "Proceedings of the 14th Annual Conference on Computational Learning Theory",
    volume = "2111",
    publisher = "Springer",
    address = "Berlin, NY",
    pages = "427--443",
    year = "2001"
}


@article{TZ01a,
  title={Text Categorization Based on Regularized Linear Classification Methods},
  author={Zhang, Tong and Oles, Frank J.},
  journal={Information Retrieval},
  volume={4},
  number={1},
  pages={5--31},
  year={2001},
  publisher={Springer}
}


@article{TZ01a-short,
  title={Text Categorization Based on Regularized Linear Classification Methods},
  author={Zhang, Tong and Oles, Frank J.},
  journal={IR},
  volume={4},
  year={2001}
}

@article{TZ02a,
author={Tong Zhang},
title = "On the dual formulation of regularized linear systems with convex risks",
journal = "Machine Learning",
volume = "46",
number = "1--3",
pages = "91--129",
year = "2002"
}


@Article{ZT04a,
  author = 	 {Tong Zhang},
  title = 	 {Statistical behavior and consistency of
classification methods based on convex risk minimization},
  journal = 	 {The Annals of Statistics},
  year = 	 {2004},
  volume =	 {32},
  number =	 {1},
  pages =	 {56--134}
}

@inproceedings{ZT04b,
author={Tong Zhang},
title = {Solving Large Scale Linear Prediction
Problems Using Stochastic Gradient Descent
Algorithms},
booktitle = {Proceedings of the 21th International
Conference on Machine Learning (ICML)},
year={2004}
}

@inproceedings{ZT04b-short,
author={Tong Zhang},
title = {Solving Large Scale Linear Prediction
Problems Using Stochastic Gradient Descent
Algorithms},
booktitle = {ICML},
year={2004}
}

@article{TZ05a,
 author = {Tong Zhang and Bin Yu},
 journal = {The Annals of Statistics},
 number = {4},
 pages = {1538--1579},
 title = {Boosting with early stopping: convergence and consistency},
 volume = {33},
 year = {2005}
}

@article{TZ05a-short,
 author = {Tong Zhang and Bin Yu},
 journal = 	 {Ann. Statist.},
 title = {Boosting with early stopping: convergence and consistency},
 pages = {1538--1579},
 volume = {33},
 year = {2005}
}

@inproceedings{WZ13a,
    title={Optimizing top-n collaborative filtering via dynamic negative item sampling},
    author={Zhang, Weinan and Chen, Tianqi and Wang, Jun and Yu, Yong},
    booktitle={Proceedings of the 36th international ACM SIGIR conference on Research and development in information retrieval},
    pages={785--788},
    year={2013}
}

@inproceedings{WZ13a-short,
    title={Optimizing top-n collaborative filtering via dynamic negative item sampling},
    author={Zhang, Weinan and Chen, Tianqi and Wang, Jun and Yu, Yong},
    booktitle={SIGIR},
    year={2013}
}

@inproceedings{WZ14a,
 author = {Weinan Zhang and Shuai Yuan and Jun Wang},
 title = {Optimal Real-Time Bidding for Display Advertising},
 booktitle = {Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)},
 year = {2014}
} 

@inproceedings{WZ16a,
  title={Deep learning over multi-field categorical data: A Case Study on User Response Prediction},
  author={Zhang, Weinan and Du, Tianming and Wang, Jun},
  booktitle={Proceedings of European Conference on Information Retrieval},
  pages={45--57},
  year={2016}
}

@inproceedings{WZ16a-short,
  title={Deep learning over multi-field categorical data: A Case Study on User Response Prediction},
  author={Zhang, Weinan and Du, Tianming and Wang, Jun},
  booktitle={ECIR},
  year={2016}
}

@inproceedings{WZ16b,
title={Bid-aware gradient descent for unbiased learning with censored data in display advertising},
author={Zhang, Weinan and Zhou, Tianxiong and Wang, Jun and Xu, Jian},
booktitle={Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)},
pages={665--674},
year={2016}
}

@inproceedings{WZ16b-short,
title={Bid-aware gradient descent for unbiased learning with censored data in display advertising},
author={Zhang, Weinan and Zhou, Tianxiong and Wang, Jun and Xu, Jian},
booktitle={KDD},
year={2016}
}

@article{XZ21a,
      title={Learning Based Proximity Matrix Factorization for Node Embedding}, 
      author={Xingyi Zhang and Kun Xie and Sibo Wang and Zengfeng Huang},
      year={2021},
      journal = {arXiv preprint arXiv:2106.05476},
}

@inproceedings{YZ18a,
author = {Zhang, Yi and Lu, Jianguo and Shai, Ofer},
title = {Improve Network Embeddings with Regularization},
year = {2018},
booktitle = {Proceedings of the 27th ACM International Conference on Information and Knowledge Management (CIKM)},
pages = {1643--1646}
}

@Article{YZ98a,
  author = 	 {Yin Zhang},
  title = 	 {On Extending Some Primal-Dual Interior-Point
                  Algorithms From Linear  Programming to Semidefinite Programming},
  journal = 	 {SIAM J. Optim.},
  year = 	 {1998},
  volume =	 {8},
  number =	 {2},
  pages =	 {365--386}
}

@inproceedings{YZ12a,
  title={{DiSCO}: Distributed Optimization for Self-Concordant Empirical Loss},
  author={Zhang, Yuchen and Xiao, Lin},
  booktitle={Proceedings of the Thirty Second International Conference on Machine Learning (ICML)},
  pages={362--370},
  year={2015}
}

@inproceedings{YZ12a-short,
  title={{DiSCO}: Distributed Optimization for Self-Concordant Empirical Loss.},
  author={Zhang, Yuchen and Lin, Xiao},
  booktitle={ICML},
  pages={362--370},
  year={2015}
}

@article{YZ19a,
title = {Degree-biased random walk for large-scale network embedding},
journal = {Future Generation Computer Systems},
volume = {100},
pages = {198--209},
year = {2019},
author = {Yunyi Zhang and Zhan Shi and Dan Feng and Xiu-Xiu Zhan},
}

@article{ZZ18a,
  title={Collective behavior learning by differentiating personal preference from peer influence},
  author={Zhang, Zan and Liu, Lin and Wang, Hao and Li, Jiuyong and Hu, Daning and Yan, Jiaqi and Algesheimer, Rene and Meierer, Markus},
  journal={Knowledge-Based Systems},
  volume={159},
  pages={233--243},
  year={2018}
}

@article{ZZ18b,
title = {Multi-label relational classification via node and label correlation},
journal = {Neurocomputing},
volume = {292},
pages = {72--81},
year = {2018},
author = {Zan Zhang and Hao Wang and Lin Liu and Jiuyong Li}
}

@InProceedings{ZZ18c,
author="Zhang, Zan
and Li, Jiuyong
and Wang, Hao
and Liu, Lin
and Liu, Jixue",
title="Which Type of Classifier to Use for Networked Data, Connectivity Based or Feature Based?",
booktitle="Proceedings of the Web Information Systems Engineering",
year="2018",
pages="364--380"
}

@Article{ZZ07a,
  author = {Zhihua Zhang and James T. Kwok and Dit-Yan Yeung},
  title = {Surrogate maximization/minimization algorithms and extensions},
  journal = {Machine Learning},
  year = {2007},
  volume = {69},
  pages = {1--33},
  number = {1},
  publisher = {Springer Netherlands},
  month = {October}
}

@INPROCEEDINGS{ZZ18d,  
author={Zhang, Ziwei and Cui, Peng and Li, Haoyang and Wang, Xiao and Zhu, Wenwu},
booktitle={Proceddings of IEEE International Conference on Data Mining (ICDM)},   
title={Billion-Scale Network Embedding with Iterative Random Projection},
year={2018},  
pages={787--796}  
}

@inproceedings{JZ13a,
author = {Zhao, Jianyu and Wang, Peng and Huang, Kai},
title = {A Semi-supervised Approach for Author Disambiguation in {KDD CUP} 2013},
booktitle = {Proceedings of the KDD Cup 2013 Workshop},
pages = {10:1--10:8},
year = {2013},
publisher = {ACM},
} 

@article{PZ06a,
author = {Peng Zhao and Bin Yu},
title = {On Model Selection Consistency of Lasso},
journal = {Journal of Machine Learning Research},
volume = {7},
year = {2006},
pages = {2541--2563}
}


@article{PZ07a,
author = {Peng Zhao and Bin Yu},
title = {Stagewise Lasso},
journal = {Journal of Machine Learning Research},
volume = {8},
year = {2007},
pages = {2701--2726},
publisher = {MIT Press},
address = {Cambridge, MA, USA},
}


@TechReport{QZ96,
author      = {Q. Zhao and S. E. Karisch and F. Rendl and H. Wolkowicz},
address     = {Waterloo, Ontario, N2L 3G1 Canada},
institution = {University of Waterloo, 
	       Department of Combinatorics and Optimization}, 
title       = {Semidefinite programming relaxations for the quadratic
	       assignment problem}, 
year        = {1996}
}


@inproceedings{TZ14a,
title={Leveraging social connections to improve personalized ranking for collaborative filtering},
author={Zhao, Tong and McAuley, Julian and King, Irwin},
booktitle={Proceedings of the 23rd ACM International Conference on Information and Knowledge Management},
pages={261--270},
year={2014}
}

@inproceedings{ZZ19a,
title={Recommending what video to watch next: a multitask ranking system},
author={Zhao, Zhe and Hong, Lichan and Wei, Li and Chen, Jilin and Nath, Aniruddh and Andrews, Shawn and Kumthekar, Aditee and Sathiamoorthy, Maheswaran and Yi, Xinyang and Chi, Ed},
booktitle={Proceedings of the 13th ACM Conference on Recommender Systems},
pages={43--51},
year={2019}
}

@inproceedings{ZZ19a-short,
title={Recommending what video to watch next: a multitask ranking system},
author={Zhao, Zhe and Hong, Lichan and Wei, Li and Chen, Jilin and Nath, Aniruddh and Andrews, Shawn and Kumthekar, Aditee and Sathiamoorthy, Maheswaran and Yi, Xinyang and Chi, Ed},
booktitle={RecSys},
year={2019}
}


@Article{ZZ15a,
  title   = {Expert Finding for Question Answering via Graph Regularized
Matrix Completion},
  author  = {Zhao, Zhou and Zhang, Lijun and He, Xiaofei and Ng, Wilfred},
  journal = {IEEE Transactions on Knowledge and Data Engineering},
  volume  = {27},
  pages   = {993--1004},
  year    = {2015}
}

@Article{ZZ15a-short,
  title   = {Expert Finding for Question Answering via Graph Regularized
Matrix Completion},
  author  = {Zhao, Zhou and Zhang, Lijun and He, Xiaofei and Ng, Wilfred},
  journal = {TKDE},
  volume  = {27},
  pages   = {993--1004},
  year    = {2015}
}

@misc{SZ21a,
      title={Adversarial Graph Disentanglement}, 
      author={Shuai Zheng and Zhenfeng Zhu and Zhizhe Liu and Shuiwang Ji and Jian Cheng and Yao Zhao},
      year={2021},
      eprint={2103.07295},
      archivePrefix={arXiv},
      primaryClass={cs.LG}
}

@inproceedings{YZ08a,
author = {Zheng, Yu and Li, Quannan and Chen, Yukun and Xie, Xing and Ma, Wei-Ying},
title = {Understanding mobility based on GPS data},
booktitle = {Proceedings of the 10th International Conference on Ubiquitous Computing (UbiComp)},
year = {2008},
isbn = {978-1-60558-136-1},
location = {Seoul, Korea},
pages = {312--321},
publisher = {ACM},
address = {New York, NY, USA},
}

@inproceedings{KZ19a,
  title={Provable Non-linear Inductive Matrix Completion},
  author={Zhong, Kai and Song, Zhao and Jain, Prateek and Dhillon, Inderjit S},
  booktitle={Advances in Neural Information Processing Systems},
  pages={11439--11449},
  year={2019},
  editor = {H. Wallach and H. Larochelle and A. Beygelzimer and F. d\textquotesingle Alch\'{e}-Buc and E. Fox and R. Garnett},
  volume = {32}
}
  
@inproceedings{KZ19a-short,
  title={Provable Non-linear Inductive Matrix Completion},
  author={Zhong, Kai and Song, Zhao and Jain, Prateek and Dhillon, Inderjit S},
  booktitle={NIPS},
  year={2019},
}

@inproceedings{GZ18a,
title={Deep interest network for click-through rate prediction},
author={Zhou, Guorui and Zhu, Xiaoqiang and Song, Chenru and Fan, Ying and Zhu, Han and Ma, Xiao and Yan, Yanghui and Jin, Junqi and Li, Han and Gai, Kun},
booktitle={Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)},
pages={1059--1068},
year={2018}
}

@inproceedings{GZ18a-short,
title={Deep interest network for click-through rate prediction},
author={Zhou, Guorui and Zhu, Xiaoqiang and Song, Chenru and Fan, Ying and Zhu, Han and Ma, Xiao and Yan, Yanghui and Jin, Junqi and Li, Han and Gai, Kun},
booktitle={KDD},
year={2018}
}

@inproceedings{TZ12a,
  title={Kernelized Probabilistic Matrix Factorization: Exploiting Graphs
and Side Information},
  author={Zhou, Tinghui and Shan, Hanhuai and Banerjee, Arindam and Sapiro,
Guillermo},
  booktitle = {SIAM International Conference on Data Mining},
  pages={403--414},
  year={2012}
}

@inproceedings{TZ12a-short,
  title={Kernelized Probabilistic Matrix Factorization: Exploiting Graphs
and Side Information},
  author={Zhou, Tinghui and Shan, Hanhuai and Banerjee, Arindam and Sapiro,
Guillermo},
  booktitle = {SDM},
  year={2012}
}

@article{WZ19a,
title={Bayesian pairwise learning to rank via one-class collaborative filtering},
author={Zhou, Wang and Li, Jianping and Zhou, Yongluan and Memon, Muhammad Hammad},
journal={Neurocomputing},
volume={367},
pages={176--187},
year={2019}
}

@inproceedings{YZ08b,
author = {Yunhong Zhou and Dennis Wilkinson and Robert Schreiber and Rong Pan},
 title = {Large-Scale Parallel Collaborative Filtering for the {N}etflix Prize},
 booktitle = {Proceedings of the Fourth International Conference on Algorithmic Aspects in Information and Management},
 year = {2008},
 pages = {337--348}
} 

@inproceedings{YZ08b-short,
	author = {Yunhong Zhou and Dennis Wilkinson and Robert Schreiber and Rong Pan},
	title = {Large-Scale Parallel Collaborative Filtering for the {N}etflix Prize},
	booktitle = {AAIM},
	year = {2008}
}

@article{CZ97a,
  title={{Algorithm 778: L-BFGS-B: Fortran subroutines for large-scale bound-constrained optimization}},
  author={Zhu, C. and Byrd, R.H. and Lu, P. and Nocedal, J.},
  journal={ACM Transactions on Mathematical Software},
  volume={23},
  number={4},
  pages={550--560},
  year={1997},
  publisher={ACM Press New York, NY, USA}
}

@inproceedings{DZ18a,
  title={Deep variational network embedding in wasserstein space},
  author={Zhu, Dingyuan and Cui, Peng and Wang, Daixin and Zhu, Wenwu},
  booktitle={Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)},
  pages={2827--2836},
  year={2018}
}

@inproceedings{HZ21a,
  title={REFINE: random range finder for network embedding},
  booktitle = {Proceedings of the 30th ACM International Conference on Conference on Information and Knowledge Management (CIKM)},
  author={Zhu, Hao and Koniusz, Piotr},
  year={2021}
}

@InProceedings{JZ01a,
  author = "Ji Zhu and Trevor Hastie",
  title = "Kernel Logistic Regression and the Import Vector Machine",
  booktitle = 	 {{NIPS} 2001},
  year =	 {2001},
  pages={1081--1088},
  url = "citeseer.nj.nec.com/543493.html" 
}

@incollection {JZ03b,
  author = " Ji Zhu and  Saharon Rosset and  Trevor Hastie and  Rob Tibshirani",
  title = " 1-norm Support Vector Machines",
  booktitle = "Advances in Neural Information Processing Systems 16",
  editor = "Sebastian Thrun and Lawrence Saul and Bernhard {Sch\"{o}lkopf}",
  publisher = "MIT Press",
  address = "Cambridge, MA",
  year = "2004",
  keywords = "classification, support vector machines, feature selection, 1-norm SVM, regularization, curse of dimensionality",
  }

@inbook{JZ21a,
author = {Jing Zhu and Xingyu Lu and Mark Heimann and Danai Koutra},
title = {Node Proximity Is All You Need: Unified Structural and Positional Node and Graph Embedding},
booktitle = {Proceedings of the SIAM International Conference on Data Mining (SDM)},
year = {2021},
pages = {163--171}
}

@mastersthesis{YZ16a,
author      = {Ya Zhu},
school      = {Graduate Institute of Networking and Multimedia,
National Taiwan University},
title       = {An Efficient Newton Method with Novel Trust Region Update Rules for Large-scale Linear Classification},
year        = {2016}
}


@INPROCEEDINGS{ZAZ09a,
  author = {Zeyuan A. Zhu and Weizhu Chen and  Gang Wang and Chenguang
Zhu and Zheng Chen},
  title = {P-pack{SVM}: Parallel Primal grAdient desCent Kernel {SVM}},
  booktitle = {Proceedings of the IEEE International Conference on Data Mining},
  year = {2009}
}

@INPROCEEDINGS{ZAZ09a-short,
  author = {Zeyuan A. Zhu and Weizhu Chen and  Gang Wang and Chenguang Zhu and Zheng Chen},
  title = {P-pack{SVM}: Parallel Primal grAdient desCent Kernel {SVM}},
  booktitle = {ICDM},
  year = {2009}
}



@InProceedings{YZ13a,
  author = 	 {Yong Zhuang and Wei-Sheng Chin and Yu-Chin Juan and Chih-Jen Lin},
  title = 	 {A fast parallel {SGD} for matrix factorization in shared memory systems},
  OPTcrossref =  {},
  OPTkey = 	 {},
  booktitle =	 {Proceedings of the ACM Recommender Systems},
  OPTpages = 	 {},
  year =	 {2013},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  url = {http://www.csie.ntu.edu.tw/~cjlin/papers/libmf.pdf},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTaddress = 	 {},
  OPTmonth = 	 {},
  OPTorganization = {},
  OPTpublisher = {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@InProceedings{YZ13a-short,
  author = 	 {Yong Zhuang and Wei-Sheng Chin and Yu-Chin Juan and Chih-Jen Lin},
  title = 	 {A fast parallel {SGD} for matrix factorization in shared memory systems},
  booktitle =	 {RecSys},
  year =	 {2013}
}

@InProceedings{YZ14a,
  author = 	 {Yong Zhuang and Wei-Sheng Chin and Yu-Chin Juan and Chih-Jen Lin},
  title = 	 {Distributed {N}ewton method for regularized logistic regression},
    booktitle =	 {Proceedings of the Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD)},
  year =	 {2015}
}

@InProceedings{YZ14a-short,
  author = 	 {Yong Zhuang and Wei-Sheng Chin and Yu-Chin Juan and Chih-Jen Lin},
  title = 	 {Distributed {N}ewton method for regularized logistic regression},
      booktitle = {PAKDD},
  year =	 {2015}
}

@inproceedings{YZ17a,
  author = 	 {Yong Zhuang and Yuchin Juan and Guo-Xun Yuan and Chih-Jen Lin},
  title = 	 {Naive Parallelization of Coordinate Descent Methods and an Application on Multi-core L1-regularized Classification},
 booktitle = {Proceedings of the 27th ACM International Conference on Conference on Information and Knowledge Management (CIKM)},
  year = 	 {2018},
  url = {http://www.csie.ntu.edu.tw/~cjlin/papers/l1_multicore_cikm.pdf},  
  OPTkey = 	 {},
  OPTtype = 	 {},
  OPTnumber = 	 {},
  OPTaddress = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@inproceedings{YZ17a-short,
  author = 	 {Yong Zhuang and Yuchin Juan and Guo-Xun Yuan and Chih-Jen Lin},
  title = 	 {Naive Parallelization of Coordinate Descent Methods and an Application on Multi-core L1-regularized Classification},
 booktitle = {CIKM},
  year = 	 {2018}
}

@inproceedings{ZZ10a,
author = {Zhuang, Zhenyun and Kim, Kyu-Han and Singh, Jatinder Pal},
title = {Improving energy efficiency of location sensing on smartphones},
booktitle = {Proceedings of the 8th international conference on Mobile systems, applications, and services},
series = {MobiSys '10},
year = {2010},
isbn = {978-1-60558-985-5},
location = {San Francisco, California, USA},
pages = {315--330},
numpages = {16},
url = {http://doi.acm.org/10.1145/1814433.1814464},
doi = {10.1145/1814433.1814464},
acmid = {1814464},
publisher = {ACM},
address = {New York, NY, USA},
keywords = {energy efficiency, location sensing, location-based applications, smartphone},
}

@article{WZ19b,
  title={Context attention heterogeneous network embedding},
  author={Zhuo, Wei and Zhan, Qianyi and Liu, Yuan and Xie, Zhenping and Lu, Jing},
  journal={Computational Intelligence and Neuroscience},
  year={2019},
  doi = {10.1155/2019/8106073},  
}

@InProceedings{AZ99a,
  author = 	 {Zien, A. and G. R\"{a}tsch and S. Mika and
     B. Sch\"{o}lkopf and C. Lemmen and A. Smola      and T. Lengauer and K.-R. M\"{u}ller},
  title = 	 {Engineering Support Vector Machine
     Kernels That Recognize Translation
     Initiation Sites
},
  booktitle = 	 {German Conference on Bioinformatics},
  year =	 {1999}
}

@incollection{MZ10a,
 title = {Parallelized Stochastic Gradient Descent},
 author = {Martin Zinkevich and Markus Weimer and Alex Smola and Lihong Li},
 booktitle = {Advances in Neural Information Processing Systems 23},
 editor = {J. Lafferty and C. K. I. Williams and J. Shawe-Taylor and
R.S. Zemel and A. Culotta},
 pages = {2595--2603},
 year = {2010}
}

@incollection{MZ10a-short,
 title = {Parallelized Stochastic Gradient Descent},
 author = {Martin Zinkevich and Markus Weimer and Alex Smola and Lihong Li},
 booktitle = {NIPS},
 year = {2010}
}

@article{HZ05a,
  title = {Regularization and Variable Selection via the Elastic Net},
  author = {Zou, Hui and Hastie, Trevor},
  journal = {Journal of the Royal Statistical Society: Series B
(Statistical Methodology)},
  volume = {67},
  number = {2},
  pages = {301--320},
  year = {2005}
}


@article{XZ93a,
  title={Numerical experience with limited-memory quasi-{N}ewton and truncated {N}ewton methods},
  author={Zou, Xiaolei and Navon, I. Michael and Berger, M. and Phua, P. K. H. and Schlick, Tamar and Le Dimet, F.X.},
  journal={SIAM Journal on Optimization},
  volume={3},
  number={3},
  pages={582--608},
  year={1993}
}


@Book{GZ60a,
  author =	 {G. Zoutendijk},
  title = 	 {Methods of feasible directions},
  publisher = 	 {Elsevier},
  year = 	 {1960}
}

@inproceedings{AZ09a,
  title={Enhancing Navigation on {W}ikipedia with Social Tags},
  author={Zubiaga, Arkaitz},
  booktitle={Proceedings of Wikimania},
  year={2009}
}

% cross reference books
		  
@Book{BS98a,
  editor = 	 {Bernhard Sch\"{o}lkopf and Christopher J. 
		  C. Burges and Alexander J. Smola},
  title = 	 "Advances in Kernel Methods - Support 
		  Vector Learning",
  publisher = 	 "MIT Press",
  year = 	 "1998",
  address =	 "Cambridge, MA"
}


% add by Paul; eunite 1

@InProceedings{ALa01,
  author =	 {Ahamd Lotfi},
  title =	 {Application of Learning Fuzzy Inference Systems in Electricity Load Forecast},
  crossref =	 {PS02a},
  pages= {123--130}
}
%  howpublished = {Report for EUNITE 2001 Competition},

@InProceedings{ALb01,
  author =	 {Achim Lewandowski and Frank Sandner and Peter Protzel},
  title =	 {Prediction of Electricity Load by Modeling the Temperature Dependencies},
  crossref =	 {PS02a},
  pages= {107--114}
}

@InProceedings{EC01,
  author =	 {Enrique Castillo and Bertha Guijarro and Amparo Alonso},
  title =	 {Electricity Load Forecast using Functional Networks},
  crossref =	 {PS02a},
  pages= {75--84}
}

@InProceedings{DE01,
  author =	 {David Esp},
  title =	 {Adaptive Logic Networks for East Slovakian Electrical Load Forecasting},
  crossref =	 {PS02a},
  pages= {55--74}
}

@InProceedings{DZ01,
  author =	 {Dalibor {\v Z}iv{\v c}\'ak},
  title =	 {Electricity Load Forecasting using {ANN}},
  crossref =	 {PS02a},
  pages= {219--231}
}

@InProceedings{EP01,
  author =	 {Emil Pelik\'an},
  title =	 {Middle-Term Electrical Load Forecasting by Time Series Decomposition},
  crossref =	 {PS02a},
  pages= {167--176}
}


@InProceedings{FR01,
  author =	 {Fabio Rivieccio},
  title =	 {{SVM} for an Electricity Load Forecast Problem},
  crossref =	 {PS02a},
  pages= {177--186}
}

@InProceedings{GAI01,
  author =	 {G. A. Ivakhnenko},
  title =	 {Inductive Self-Organising Algorithm for Maximum Electrical Load Prediction},
  crossref =	 {PS02a},
  pages= {85--92}
}

@InProceedings{GB01,
  author =	 {Gianluca Bontempi},
  title =	 {EUNITE World-Wide competition: Research report},
  crossref =	 {PS02a},
  pages= {33--40}
}

@InProceedings{IK01,
  author =	 {Iain King and John Tindle},
  title =	 {Storage of Half Hourly Electric Metering Data and Forecasting with Artificial Neural Network Technology},
  crossref =	 {PS02a},
  pages= {93--106}
}

@InProceedings{RCW01,
  author =	 {Robert C. Weizenegger},
  title =	 {Maximum Electricity Load Problem},
  crossref =	 {PS02a},
  pages= {187--208}
}

@InProceedings{WB01,
  author =	 {Werner Brockmann and Steffen Kuthe},
  title =	 {Different Models to Forecast Electricity Loads},
  crossref =	 {PS02a},
  pages= {41--54}
}

@InProceedings{WK01,
  author =	 {Wojciech Kowalczyk},
  title =	 {Averaging and data enrichment: two approaches to electricity load forecasting},
  crossref =	 {PS02a},
  pages= {209--218}
}


@Misc{ZB01,
  author =	 {Zvi Boger},
  title =	 {Electricity Load Forecast using Artificial Neural
Networks Clustering},
  year={2001},
note =	 {Available at {\tt http://neuron.tuke.sk/competition/}}
}
%  crossref =	 {PS02a},


@Article{KJ88,
  author = 	 {Kamal Jabbour and Jose Fernando Vega Riveros and David Landsbergen and Walter Meyer},
  title = 	 {ALFA: Automated Load Forecasting Assistant},
  journal = 	 {IEEE Transactions on Power Systems},
  year = 	 {1988},
  volume =	 {3},
  number =	 {3},
  pages =	 {908--914},
  month =	 {August}
}

@article{JK92a,
  title={Estimating the largest eigenvalue by the power and Lanczos algorithms with a random start},
  journal={SIAM journal on matrix analysis and applications},
  author={Kuczynski, Jacek and Henryk Wozniakowski},
  volume={13},
  number={4},
  pages={1094--1122},
  year={1992},
  publisher={SIAM}
}


@Article{SR93,
  author = 	 {S. Rahman and O. Hazim},
  title = 	 {A Generalized Knowledge-Based Short-Term Load-Forecasting Technique},
  journal = 	 {IEEE Transactions on Power Systems},
  year = 	 {1993},
  volume =	 {8},
  number =	 {2},
  pages =	 {508--514},
  month =	 {May}
}

@Article{NA01,
  author = 	 {Nima Amjady},
  title = 	 {Short-Term Hourly Load Forecasting Using Time-Series Modeling with Peak Load Estimation Capability},
  journal = 	 {IEEE Transactions on Power Systems},
  year = 	 {2001},
  volume =	 {16},
  number =	 {3},
  pages =	 {498--505},
  month =	 {August}
}

@article{st:es,
author      = {Charles M. Stein},
journal     = {The Annals of Statistics},
pages       = {1135--1151},
title       = {Estimation of the mean of a multivariate normal
               distribution},
volume      = {9},
year        = {1981}
}

%EUNITE 2002

@Misc{MW02,
  author =	 {Marcin Wojnarski},
  title =	 {Modeling the Bank Client's Behavior with LTF-C Neural
Network},
  year =	 {2002}
}
@Misc{JG02,
  author =	 {Jo{\~a}o Gama},
  title =	 {Modeling the Bank's Client behavior using Functional
Trees},
  year =	 {2002}
}
@Misc{DE02,
  author =	 {David Esp},
  title =	 {Adaptive Logic Networks in Bank Customer Modeling},
  year =	 {2002}
}
@Misc{NJ02,
  author =	 {Nico Jacobs and Hendrik Blockeel},
  title =	 {When Hammers Are Used To Hit Nails: A classic approach to
a classic problem},
  year =	 {2002}
}
@Misc{DW02,
  author =	 {David West},
  title =	 {Ensemble Methods for Identifying Customer Activity
Levels},
  year =	 {2002}
}
@Misc{IC02,
  author =	 {Ireneusz Czarnowski and Piotr Jedrzejowicz},
  title =	 {{PLAANN} as a Classification Tool for Customer Intelligence
in Banking},
  year =	 {2002}
}
@Misc{TMJ02,
  author =	 {Thomas Martini J{\o}rgensen},
  title =	 {EUNITE Competition 2002: An N-Tuple Ensemble Classifier
Model for Predicting whether a Bank Client is Active or Not},
  year =	 {2002}
}
@Misc{XL02,
  author =	 {Xiaozhong Li},
  title =	 {Modeling Bank Client Behavior using a Search-Based Neural
Network},
  year =	 {2002}
}


% papers which used libsvm

@article{libsvmDA03a,
 author = {Davide Anguita and Sandro Ridella and Fabio Rivieccio and Rodolfo Zunino},
 title = {Quantum optimization for training support vector machines},
 journal = {Neural Netw.},
 volume = {16},
 number = {5--6},
 year = {2003},
 issn = {0893-6080},
 pages = {763--770},
 doi = {http://dx.doi.org/10.1016/S0893-6080(03)00087-X},
 publisher = {Elsevier Science Ltd.},
 }

@InCollection{libsvmTL03a,
  author = 	 {Luo, T. and Kramer, K. and Goldgof, D. and Hall, L. O. and Samson, S. and Remson, A. and Hopkins, T.},
  title = 	 {Learning to Recognize Plankton},
  booktitle = 	 {Proceedings of IEEE International Confernece on SMC},
  url={http://www.csee.usf.edu/~hall/papers/plankton03a.pdf},
  year =	 {2003}
}


@inproceedings{libsvmCRPIT-32-145-150,
   Author = {Xie, Huayang and Andreae, Peter and Zhang, Mengjie and Warren, Paul},
   Title = {Detecting Stress in Spoken English using Decision Trees and Support Vector Machines},
   BookTitle = {Australasian Workshop on Data Mining and Web Intelligence (DMWI2004)},
   Editor = {Purvis, Martin},
   Series= {CRPIT},
   Address= {Dunedin, New Zealand},
   Publisher = {ACS},
   Volume = {32},
   Pages = {145--150},
url= {http://crpit.com/confpapers/CRPITV32Xie.pdf},
   Year = {2004} }


   	
@InCollection{libsvmJL03a,
  author = 	 {Jianmin Li and Bo Zhang and Fuzong Lin},
  title = 	 {A New Cache Replacement Algorithm in {SMO}},
  booktitle = 	 {Lecture Notes in Computer Science},
  OPTcrossref =  {},
  OPTkey = 	 {},
  OPTpages = 	 {},
  publisher =	 {Springer-Verlag Heidelberg},
  year =	 {2003},
  editor =	 {S.-W. Lee and A. Verri},
  volume =	 {2388},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTtype = 	 {},
  OPTchapter = 	 {},
  OPTaddress = 	 {},
  OPTedition = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}



@InCollection{libsvmMF03a,
  author = 	 {Mike Fugate and James R. Gattiker},
  title = 	 {Anomaly Detection Enhanced Classification in Computer Intrusion Detection},
  booktitle = 	 {Lecture Notes in Computer Science},
  OPTcrossref =  {},
  OPTkey = 	 {},
  OPTpages = 	 {},
  publisher =	 {Springer-Verlag Heidelberg},
  year =	 {2003},
  editor =	 {S.-W. Lee and A. Verri},
  volume =	 {2388},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTtype = 	 {},
  OPTchapter = 	 {},
  OPTaddress = 	 {},
  OPTedition = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@ARTICLE{libsvmDM03a,
  AUTHOR = {David Meyer and Friedrich Leisch and Kurt Hornik},
  TITLE = {The Support Vector Machine under Test},
  JOURNAL = {Neurocomputing},
  YEAR = 2003,
  PAGES = {169--186},
  VOLUME = 55
}

@InCollection{libsvmML03a,
  author = 	 {Martina Liepert},
  title = 	 {Topological Fields Chunking for German with SVM's: Optimizing SVM-parameters with GA's},
  booktitle = 	 {Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2003)},
  OPTcrossref =  {},
  OPTkey = 	 {},
  OPTpages = 	 {},
  OPTpublisher = {},
  year =	 {2003},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTtype = 	 {},
  OPTchapter = 	 {},
  OPTaddress = 	 {},
  OPTedition = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@Article{libsvmTL04a,
  author = 	 {Luo, Tong and Kramer, Kurt and Goldgof, Dmitry B and Hall, Lawrence O and Samson, Scott and Remsen, Andrew and Hopkins, Thomas},
  title = 	 {Recognizing Plankton Images from the Shadow Image Particle Profiling Evaluation Recorder},
  journal = 	 {IEEE Transactions in System Man and Cybernetics, B},
  year = 	 {2004},
url={http://figment.csee.usf.edu/~goldgof/papers/planktonvim-bw-2004-revised.pdf},
  OPTkey = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTpages = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

 
@InCollection{libsvmZY03a,
  author = 	 {Zhonghua Yu and  Yoshimasa Tsuruoka and Jun'ichi Tsujii},
  title = 	 {Automatic Resolution of Ambiguous Abbreviations in Biomedical Texts using Support Vector Machines and One Sense Per Discourse Hypothesis},
  booktitle = 	 {Proceedings of the SIGIR'03 Workshop on Text Analysis and Search for Bioinformatics},
  OPTcrossref =  {},
  OPTkey = 	 {},
  pages =	 {57--62},
  OPTpublisher = {},
  year =	 {2003},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTtype = 	 {},
  OPTchapter = 	 {},
  OPTaddress = 	 {},
  OPTedition = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}



@Article{libsvmAB03a,
  author = 	 {Bleckmann, A. and  Meiler, J.},
  title = 	 {Epothilones: QSAR Studies Performed by Artificial Neural Networks Leading to New Drug Proposals},
  journal = 	 {QSAR Comb. Sci.},
  year = 	 {2003},
url={www.jens-meiler.de/bleckmann_a_2003_qsar.pdf},
  OPTkey = 	 {},
  volume =	 {22},
  OPTnumber = 	 {},
  pages =	 {719--721},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}



@Article{libsvmbi04a,
  author = 	 {},
  title = 	 {},
  journal = 	 {Bioinformatics.2004},
  year = 	 {2004},
url={http://bioinformatics.oupjournals.org/cgi/reprint/20/4/586.pdf},
  OPTkey = 	 {},
  volume =	 {20},
  OPTnumber = 	 {},
  pages =	 {445--598},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}


@Article{libsvmman01a,
url={www.jmlr.org/papers/volume2/manevitz01a/manevitz01a.pdf},
  author = 	 {},
  title = 	 {},
  journal = 	 {Journal of Machine Learning Research},
  year = 	 {},
  OPTkey = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTpages = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@InCollection{libsvmJH04a,
url={http://www.cs.unc.edu/~prins/Publications/PSB04.pdf},
  author = 	 {Huan, Jun and Wang, Wei and Washington, Anglina and Prins, Jan and Shah, Ruchir and Tropsha, Alexander},
  title = 	 {Accurate Classification of Protein Structural Families Using Coherent Subgraph Analysis},
  booktitle = 	 {Proceedings of the Pacific Symposium on Biocomputing (PSB)},
  OPTcrossref =  {},
  OPTkey = 	 {},
  OPTpages = 	 {},
  OPTpublisher = {},
  year =	 {2004},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTtype = 	 {},
  OPTchapter = 	 {},
  OPTaddress = 	 {},
  OPTedition = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}


@InCollection{libsvmicml04,
url={http://www.aicml.cs.ualberta.ca/banff04/icml/pages/papers/294.pdf},
  author = 	 {},
  title = 	 {Nonparametric Classification with Polynomial MPMC Cascades},
  booktitle = 	 {ICML},
  OPTcrossref =  {},
  OPTkey = 	 {},
  OPTpages = 	 {},
  OPTpublisher = {},
  year =	 {2004},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTtype = 	 {},
  OPTchapter = 	 {},
  OPTaddress = 	 {},
  OPTedition = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@InCollection{libsvmAC03a,
  author = 	 {Ana Cardoso-Cachopo and Arlindo L. Oliveira},
  title = 	 {An Empirical Comparison of Text Categorization Methods},
  booktitle = 	 {SPIRE 2003 proceedings},
  OPTcrossref =  {},
  OPTkey = 	 {},
  pages =	 {183--196},
  OPTpublisher = {Springer-Verlag},
  year =	 {2003},
  editor =	 {Mario A. Nascimento and Edleno S. de Moura and Arlindo L. Oliveira},
  volume =	 {2857},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTtype = 	 {},
  OPTchapter = 	 {},
  OPTaddress = 	 {},
  OPTedition = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@InCollection{libsvmHawaii02a,
  author = 	 {},
url={http://csdl.computer.org/comp/proceedings/hicss/2003/1874/04/187440103c.pdf},
  title = 	 {Support Vector Machines for Text Categorization},
  booktitle = 	 {Proceedings of the 36th Hawaii Internation Conference on System Science},
  OPTcrossref =  {},
  OPTkey = 	 {},
  OPTpages = 	 {},
  OPTpublisher = {},
  year =	 {2002},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTtype = 	 {},
  OPTchapter = 	 {},
  OPTaddress = 	 {},
  OPTedition = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@InCollection{libsvmpw03a,
url={http://media.cs.tsinghua.edu.cn/~cairui/download/papers/PCM2003_NewsClassification.pdf},
  author = 	 {Peng Wang et al.},
  title = 	 {},
  booktitle = 	 {ICICS-PCM},
  OPTcrossref =  {},
  OPTkey = 	 {},
  OPTpages = 	 {},
  OPTpublisher = {},
  OPTyear = 	 {2003},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTtype = 	 {},
  OPTchapter = 	 {},
  OPTaddress = 	 {},
  OPTedition = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@InCollection{libsvmDE02a,
  author = 	 {
Damian Eads and  Daniel Hill and  Sean Davis and  Simon Perkins and  Junshui Ma and  Reid Porter and  James Theiler
},
  title = 	 {Genetic Algorithms and Support Vector Machines for Time Series Classification},
  booktitle = 	 {Proc. SPIE 4787; Fifth Conference on the Applications and Science of Neural Networks, Fuzzy Systems, and Evolutionary Computation; Signal Processing Section; Annual Meeting of SPIE},
url={http://www.zeus.lanl.gov/green/publications/eadsSPIE4787.pdf},
  OPTcrossref =  {},
  OPTkey = 	 {},
  OPTpages = 	 {},
  OPTpublisher = {},
  year =	 {2002},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTtype = 	 {},
  OPTchapter = 	 {},
  OPTaddress = 	 {},
  OPTedition = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}


@InCollection{libsvmtl03b,
  author = 	 {},
  title = 	 {Detecting Emotion in Music},
  booktitle = 	 {ISMIR},
url={http://ismir2003.ismir.net/papers/Li.PDF},
  OPTcrossref =  {},
  OPTkey = 	 {},
  OPTpages = 	 {},
  OPTpublisher = {},
  year =	 {2003},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTtype = 	 {},
  OPTchapter = 	 {},
  OPTaddress = 	 {},
  OPTedition = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@InCollection{libsvmBL03a,
url={http://www.cs.uic.edu/~liub/publications/icml-03.pdf},
  author = 	 {},
  title = 	 {Learning with Positive and Unlabeled Examples Using Weighted },
  booktitle = 	 {ICML},
  OPTcrossref =  {},
  OPTkey = 	 {},
  OPTpages = 	 {},
  OPTpublisher = {},
  year =	 {2003},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTtype = 	 {},
  OPTchapter = 	 {},
  OPTaddress = 	 {},
  OPTedition = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@InCollection{libsvmSL02a,
url={http://www.cs.dartmouth.edu/~farid/publications/ih02.html},
  author = 	 {    S. Lyu and H. Farid },
  title = 	 {Detecting Hidden Messages Using Higher-Order Statistics and Support Vector Machines

},
  booktitle = 	 {    5th International Workshop on Information Hiding, Noordwijkerhout, The Netherlands, 2002},
  OPTcrossref =  {},
  OPTkey = 	 {},
  OPTpages = 	 {},
  OPTpublisher = {},
  OPTyear = 	 {},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTtype = 	 {},
  OPTchapter = 	 {},
  OPTaddress = 	 {},
  OPTedition = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@Article{libsvmjmlr03a,
url={http://www.jmlr.org/papers/volume3/perkins03a/perkins03a.pdf},
  author = 	 {},
  title = 	 {Grafting: Fast, Incremental Feature Selection by Gradient Descent },
  journal = 	 {JMLR},
  year = 	 {2003},
  OPTkey = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTpages = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@InCollection{libsvmnips03a,
url={http://books.nips.cc/papers/files/nips16/NIPS2003_AP09.pdf},
  author = 	 {},
  title = 	 {Application of SVMs for Colour Classification and Collision},
  booktitle = 	 {{NIPS}},
  OPTcrossref =  {},
  OPTkey = 	 {},
  OPTpages = 	 {},
  OPTpublisher = {},
  year =	 {2003},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTtype = 	 {},
  OPTchapter = 	 {},
  OPTaddress = 	 {},
  OPTedition = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@InCollection{libsvmtrec03a,
url={http://www-2.cs.cmu.edu/~hdw/TREC03Reportc.pdf},
  author = 	 {},
  title = 	 {},
  booktitle = 	 {TREC 2003},
  OPTcrossref =  {},
  OPTkey = 	 {},
  OPTpages = 	 {},
  OPTpublisher = {},
  OPTyear = 	 {},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTtype = 	 {},
  OPTchapter = 	 {},
  OPTaddress = 	 {},
  OPTedition = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}


@InCollection{libsvmBC04a,
url={http://www.nada.kth.se/~caputo/publik/137_caputo_b.pdf},
  author = 	 { B. Caputo, C. Wallraven, M. E. Nilsback. },
  title = 	 {Object categorization via local kernels.},
  booktitle = 	 { ICPR04},
  OPTcrossref =  {},
  OPTkey = 	 {},
  OPTpages = 	 {},
  OPTpublisher = {},
  OPTyear = 	 {},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTtype = 	 {},
  OPTchapter = 	 {},
  OPTaddress = 	 {},
  OPTedition = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@Article{libsvmJG03a,
url={http://www.enzim.hu/~tusi/papers/NAR_31_3613(2003).pdf},
  author = 	 {Gardy, JL and Spencer, C and Wang, K. and Ester. M and Tusn\x{00E1}dy GE and Simon, I and Hua, S and deFays, K and Lambert, C and Nakai, K and Brinkman, FS},
  title = 	 {PSORT-B: improving protein subcellular localization prediction for Gram-negative bacteria},
  journal = 	 {Nucleic Acids Res},
  year = 	 {2003},
  OPTkey = 	 {},
  volume =	 {31},
  OPTnumber = 	 {},
  pages =	 {3613--3617},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@InCollection{libsvmideal02a,
url={http://www.cse.cuhk.edu.hk/~king/PUB/ideal2002.pdf},
  author = 	 {},
  title = 	 {Support Vector Machine Regression for Volatile Stock Market},
  booktitle = 	 {IDEAL 2002},
  OPTcrossref =  {},
  OPTkey = 	 {},
  OPTpages = 	 {},
  OPTpublisher = {},
  OPTyear = 	 {},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTtype = 	 {},
  OPTchapter = 	 {},
  OPTaddress = 	 {},
  OPTedition = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@InCollection{libsvmicml03b,
url={http://www.hpl.hp.com/conferences/icml2003/papers/281.pdf},
  author = 	 {},
  title = 	 {Online Feature Selection using Grafting},
  booktitle = 	 {ICML 03},
  OPTcrossref =  {},
  OPTkey = 	 {},
  OPTpages = 	 {},
  OPTpublisher = {},
  OPTyear = 	 {},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTtype = 	 {},
  OPTchapter = 	 {},
  OPTaddress = 	 {},
  OPTedition = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@Article{libsvmasap3a,
url={http://cmgm.stanford.edu/~brutlag/Papers/Ben-Hur2003.pdf},
  author = 	 {},
  title = 	 {},
  journal = 	 {Bioinformatics},
  year = 	 {2003},
  OPTkey = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTpages = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@InCollection{libsvmcfa03a,
url={http://discover1.mc.vanderbilt.edu/discover/public/Publications/SA_LUNG_CANCER.pdf},
  author = 	 {C.F. Aliferis and  I. Tsamardinos and  P. Massion and  A. Statnikov and  N. Fananapazir and  D. Hardin},
  title = 	 {Machine Learning Models For Classification Of Lung Cancer and Selection of Genomic Markers Using Array Gene Expression Data},
  booktitle = 	 {Proceedings of the 16th International Florida Artificial Intelligence Research Society (FLAIRS) Conference, May 12-14, 2003, },
  OPTcrossref =  {},
  OPTkey = 	 {},
  pages =	 {67--71},
  publisher =	 {AAAI Press},
  OPTyear = 	 {},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTtype = 	 {},
  OPTchapter = 	 {},
  OPTaddress = 	 {},
  OPTedition = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@InCollection{libsvmtopquark02a,
url={http://www.ippp.dur.ac.uk/Workshops/02/statistics/proceedings//vaiciulis.pdf},
  author = 	 {	 A.Vaiciulis},
  title = 	 { Support Vector Machines in Analysis of Top Quark Production},
  booktitle = 	 {Proceedings of Advanced Statistical Techniques
in Particle Physics

},
  OPTcrossref =  {},
  OPTkey = 	 {},
  OPTpages = 	 {},
  OPTpublisher = {},
  year =	 {2002},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTtype = 	 {},
  OPTchapter = 	 {},
  OPTaddress = 	 {},
  OPTedition = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}


@InCollection{libsvmasci03a,
url={http://www.science.uva.nl/~cgmsnoek/pub/asci2003.pdf},
  author = 	 {C.G.M. Snoek and M. Worring
},
  title = 	 {Time Interval based Modelling and Classification of Events in Soccer Video
},
  booktitle = 	 {Proceedings of the 9th Annual Conference of the Advanced School for Computing and Imaging (ASCI), Heijen, The Netherlands},
  OPTcrossref =  {},
  OPTkey = 	 {},
  OPTpages = 	 {},
  OPTpublisher = {},
  year =	 {2003},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTtype = 	 {},
  OPTchapter = 	 {},
  OPTaddress = 	 {},
  OPTedition = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@InCollection{libsvmrecomb04a,
url={http://www.cs.unc.edu/~prins/Publications/RECOMB04.pdf},
  author = 	 { J. Huan and W. Wang and D. Bandyopadhyay and J. Snoeyink and J. Prins and A. Tropsha},
  title = 	 {Mining Protein Family Specific Residue Packing Patterns From Protein Structure Graphs},
  booktitle = 	 {Proceedings of the Intl Conf on Research in Computational Molecular Biology (RECOMB)},
  OPTcrossref =  {},
  OPTkey = 	 {},
  OPTpages = 	 {},
  OPTpublisher = {},
  year =	 {2004},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTtype = 	 {},
  OPTchapter = 	 {},
  OPTaddress = 	 {},
  OPTedition = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@InCollection{libsvmmrnv04a,
url={http://boesnach.gmxhome.de/papers/MRNV_2004_Boesnach.pdf},
  author = 	 {},
  title = 	 {ANALYSIS OF DRILL SOUND IN SPINE SURGERY},
  booktitle = 	 {MRNV},
  OPTcrossref =  {},
  OPTkey = 	 {},
  OPTpages = 	 {},
  OPTpublisher = {},
  year =	 {2004},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTtype = 	 {},
  OPTchapter = 	 {},
  OPTaddress = 	 {},
  OPTedition = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@InCollection{libsvmnips02a,
url={http://www.cs.bc.edu/~dmartin/papers/nips02.ps},
  author = 	 {},
  title = 	 {},
  booktitle = 	 {NIPS},
  OPTcrossref =  {},
  OPTkey = 	 {},
  OPTpages = 	 {},
  OPTpublisher = {},
  year =	 {2002},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTtype = 	 {},
  OPTchapter = 	 {},
  OPTaddress = 	 {},
  OPTedition = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@InCollection{libsvmspie04a,
url={http://www.cs.dartmouth.edu/~farid/publications/spie04.html},
  author = 	 {    S. Lyu and H. Farid 
},
  title = 	 {  Steganalysis Using Color Wavelet Statistics and One-Class Support Vector Machines
},
  booktitle = 	 {    SPIE Symposium on Electronic Imaging},
  OPTcrossref =  {},
  OPTkey = 	 {},
  OPTpages = 	 {},
  publisher =	 {2004},
  OPTyear = 	 {},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTtype = 	 {},
  OPTchapter = 	 {},
  OPTaddress = 	 {},
  OPTedition = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@InCollection{libsvmijcai03a,
url={http://www.cs.uic.edu/~liub/publications/ijcai03-textClass.pdf},
  author = 	 {Xiaoli Li and Bing Liu},
  title = 	 {Learning to classify text using positive and unlabeled data},
  booktitle = 	 {Proceedings of Eighteenth International Joint Conference on Artificial Intelligence (IJCAI-03)},
  OPTcrossref =  {},
  OPTkey = 	 {},
  OPTpages = 	 {},
  OPTpublisher = {},
  year =	 {Aug 9-15, 2003},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTtype = 	 {},
  OPTchapter = 	 {},
  OPTaddress = 	 {},
  OPTedition = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@InCollection{libsvmdmi,
url={www.eastman.ucl.ac.uk/~dmi/Papers/amjmedgen.PDF},
  author = 	 {},
  title = 	 {3D Analysis of Facial Morphology},
  booktitle = 	 {},
  OPTcrossref =  {},
  OPTkey = 	 {},
  OPTpages = 	 {},
  OPTpublisher = {},
  OPTyear = 	 {},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTtype = 	 {},
  OPTchapter = 	 {},
  OPTaddress = 	 {},
  OPTedition = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@Article{libsvmtox04a,
url={http://ehp.niehs.nih.gov/txg/members/2004/7036/7036.pdf},
  author = 	 {},
  title = 	 {Fingerprints of toxicant classes},
  journal = 	 {??},
  year = 	 {2004},
  OPTkey = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTpages = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@InCollection{libsvmiconip02a,
url={www.cse.cuhk.edu.hk/~king/PUB/ICONIP2002-cr1913.pdf},
  author = 	 {},
  title = 	 { Non-fixed and asymmetrical margin approach to Stock Market},
  booktitle = 	 {ICONIP},
  OPTcrossref =  {},
  OPTkey = 	 {},
  OPTpages = 	 {},
  OPTpublisher = {},
  year =	 {2002},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTtype = 	 {},
  OPTchapter = 	 {},
  OPTaddress = 	 {},
  OPTedition = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@InCollection{libsvmrecomb04b,
url={recomb04.sdsc.edu/posters/mwagnerATcchmc.org_305.pdf},
  author = 	 {Michael Wagner and Zhongming Yang},
  title = 	 {A Robust, Noise-Insensitive Variable SelectionAlgorithm for Molecular Profiling Data},
  booktitle = 	 {RECOMB},
  OPTcrossref =  {},
  OPTkey = 	 {},
  OPTpages = 	 {},
  OPTpublisher = {},
  year =	 {2004},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTtype = 	 {},
  OPTchapter = 	 {},
  OPTaddress = 	 {},
  OPTedition = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@Article{libsvmpami05a,
url={http://lmb.informatik.uni-freiburg.de/people/haasdonk/publications/indefinite-svm-report-IEEE-notice.pdf},
  author = 	 {},
  title = 	 {Space Interpretation of SVMs with Indefinite Kernels},
  journal = 	 {IEEE TPAMI.},
  year = 	 {2005},
  OPTkey = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTpages = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@InCollection{libsvmeccb03a,
url={http://www.inra.fr/Internet/Departements/bia/recherche/colloques/ECCB-2003/posters/pdf/Machi_Taher_20030606_193302.pdf},
  author = 	 {Leila Taher and Burkhard Morgenstern and Peter Meinicke},
  title = 	 {The Importance of Window Length in Splice Site Prediction},
  booktitle = 	 {ECCB},
  OPTcrossref =  {},
  OPTkey = 	 {},
  OPTpages = 	 {},
  OPTpublisher = {},
  year =	 {2003},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTtype = 	 {},
  OPTchapter = 	 {},
  OPTaddress = 	 {},
  OPTedition = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@InCollection{libsvmicdm03a,
url={http://www.csd.uwo.ca/faculty/ling/papers/icdm03a.ps},
  author = 	 {Jin Huang  and Jingjing Lu
and Charles X. Ling },
  title = 	 {Comparing Naive Bayes, Decision Trees, and SVM with AUC and Accuracy

},
  booktitle = 	 {ICDM},
  OPTcrossref =  {},
  OPTkey = 	 {},
  OPTpages = 	 {},
  OPTpublisher = {},
  year =	 {2003},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTtype = 	 {},
  OPTchapter = 	 {},
  OPTaddress = 	 {},
  OPTedition = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@InCollection{libsvmaistat03a,
url={http://research.microsoft.com/conferences/AIStats2003/proceedings/120.ps},
  author = 	 {Marina Meil},
  title = 	 {Data Centering in Feature Space

},
  booktitle = 	 {AIStat},
  OPTcrossref =  {},
  OPTkey = 	 {},
  OPTpages = 	 {},
  OPTpublisher = {},
  year =	 {2003},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTtype = 	 {},
  OPTchapter = 	 {},
  OPTaddress = 	 {},
  OPTedition = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@Article{libsvmgene04a,
  author = 	 {},
url={http://arxiv.org/pdf/q-bio.QM/0401043},
  title = 	 {A Simple Method for Finding Molecular Signatures from Gene Expression Data},
  journal = 	 {},
  year = 	 {2004},
  OPTkey = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTpages = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@Article{libsvmmat04a,
url={http://www.mae.cornell.edu/zabaras/Publications/PDFiles/Paper58.pdf},
  author = 	 {V. Sundararaghavan and N. Zabaras},
  title = 	 {A dynamic material library for the representation of single phase polyhedral microstructures},
  journal = 	 {Acta Materialia, Vol. 52/14, },
  year = 	 {2004},
  OPTkey = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  pages =	 {4111--4119},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@ONLINE{MES13a,
	author = {M. E. Stanley},
	title = {Building a virtual gyro},
    year = {2013},
        howpublished = {\url{https://community.freescale.com/community/the-embedded-beat/blog/2013/03/12/building-a-virtual-gyro}}
}

@Article{libsvmmoo04a,
url={http://www.iitk.ac.in/kangal/papers/k2004007.pdf},
  author = 	 {Stanley Y. M. Shi, P. N. Suganthan and Deb, K. },
  title = 	 {Multi-Class Protein Fold Recognition Using Multi-Objective Evolutionary Algorithms },
  journal = 	 {},
  year = 	 {},
  OPTkey = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTpages = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@InCollection{libsvmuai03a,
url={http://www.cs.brown.edu/people/tld/postscript/YoungandDeanUAI-03.pdf},
  author = 	 {Joel Young and Thomas Dean},
  title = 	 {Exploiting Locality in Searching the Web},
  booktitle = 	 {UAI},
  OPTcrossref =  {},
  OPTkey = 	 {},
  OPTpages = 	 {},
  OPTpublisher = {},
  year =	 {2003},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTtype = 	 {},
  OPTchapter = 	 {},
  OPTaddress = 	 {},
  OPTedition = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@InCollection{libsvmnaacl04a,
url={cs.baylor.edu/~girju/hlt-naacl/pdf/girju.pdf},
  author = 	 {},
  title = 	 {Support Vector Machines Applied to the Classification of Semantic Relations in Nominalized Noun Phrases},
  booktitle = 	 {NAACL},
  OPTcrossref =  {},
  OPTkey = 	 {},
  OPTpages = 	 {},
  OPTpublisher = {},
  year =	 {2004a},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTtype = 	 {},
  OPTchapter = 	 {},
  OPTaddress = 	 {},
  OPTedition = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@InCollection{libsvmmmir03a,
url={http://km.doc.ic.ac.uk/mmir2003/3urimmsigir03.pdf},
  author = 	 {Peng Dai and Uri Iurgel and Gerhard Rigoll},
  title = 	 {
A Novel Feature Combination Approach for Spoken Document Classification with Support Vector Machines},
  booktitle = 	 {Multimedia Information Retrieval Workshop 2003
in conjunction with the 26th annual ACM SIGIR},
  OPTcrossref =  {},
  OPTkey = 	 {},
  OPTpages = 	 {},
  OPTpublisher = {},
  OPTyear = 	 {},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTtype = 	 {},
  OPTchapter = 	 {},
  OPTaddress = 	 {},
  OPTedition = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@InCollection{libsvmbookchap04a,
  author = 	 {Hari Sundaram and Shih-Fu Chang},
  title = 	 {Video Analysis and Summarization at Structural and Semantic Levels},
  booktitle = 	 {a book chapter},
  OPTcrossref =  {},
  OPTkey = 	 {},
  OPTpages = 	 {},
  OPTpublisher = {},
  year =	 {??},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTtype = 	 {},
  OPTchapter = 	 {},
  OPTaddress = 	 {},
  OPTedition = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@InCollection{libsvmicme02a,
url={http://www.lienhart.de/Publications/ICME2002-ExtendedVersion.pdf},
  author = 	 {Jochen Maydt and Rainer Lienhart},
  title = 	 {A Fast Method For Training Support Vector Machines With a Very Large Set of Linear Features},
  booktitle = 	 {IEEE ICME 2002, Lousanne, Switzerland, pp. xx-yy},
  OPTcrossref =  {},
  OPTkey = 	 {},
  OPTpages = 	 {},
  OPTpublisher = {},
  year =	 {Aug. 2002},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTtype = 	 {},
  OPTchapter = 	 {},
  OPTaddress = 	 {},
  OPTedition = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@InCollection{libsvmhase04a,
url={http://www.cse.fau.edu/~zhong/papers/sqc.pdf},
  author = 	 {Shi Zhong and Taghi M. Khoshgoftaar, and Naeem Seliya},
  title = 	 {Unsupervised Learning for Expert-based Software Quality Estimation},
  booktitle = 	 {8th IEEE Int. Symp. High Assurance Systems Engineering (HASE'04)},
  OPTcrossref =  {},
  OPTkey = 	 {},
  OPTpages = 	 {},
  OPTpublisher = {},
  year =	 {2004},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTtype = 	 {},
  OPTchapter = 	 {},
  OPTaddress = 	 {},
  OPTedition = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@InCollection{libsvmicpr04a,
url={http://www.ifremer.fr/lasaa/rfablet/Papers/icpr2004_rfablet.pdf},
  author = 	 {},
  title = 	 {Automatic fish age estimation from otolith images using statistical learning},
  booktitle = 	 {ICPR04},
  OPTcrossref =  {},
  OPTkey = 	 {},
  OPTpages = 	 {},
  OPTpublisher = {},
  OPTyear = 	 {},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTtype = 	 {},
  OPTchapter = 	 {},
  OPTaddress = 	 {},
  OPTedition = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@InCollection{libsvmsigir04a,
url={http://ciir.cs.umass.edu/pubfiles/ir-351.pdf},
  author = 	 {Liu, Xiaoyong and Croft, W. Bruce and Oh, Paul and Hart, David},
  title = 	 {Automatic Recognition of Reading Levels from User Queries},
  booktitle = 	 {SIGIR},
  OPTcrossref =  {},
  OPTkey = 	 {},
  OPTpages = 	 {},
  OPTpublisher = {},
  year =	 {2004},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTtype = 	 {},
  OPTchapter = 	 {},
  OPTaddress = 	 {},
  OPTedition = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@Article{libsvmpami04a,
  author = 	 {Yefeng Zheng, Huiping Li, David Doermann},
  title = 	 {Machine Printed Text and Handwriting Identification in Noisy Document Images
},
  journal = 	 {PAMI},
  year = 	 {2004},
url={http://www.umiacs.umd.edu/lamp/pubs/TechReports/LAMP_107/LAMP_107.pdf},
  OPTkey = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTpages = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@Article{libsvmtnn04a,
url={http://www.mathcs.carleton.edu/faculty/dmusican/tr0102.ps},
  author = 	 {},
  title = 	 {Active support vector regression},
  journal = 	 {IEEETNN},
  year = 	 {2004},
  OPTkey = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTpages = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@InCollection{libsvmsdm04a,
url={http://www.siam.org/meetings/sdm04/proceedings/sdm04_055.pdf},
  author = 	 {},
  title = 	 {Classifying Documents Without Labels},
  booktitle = 	 {SIAM DM},
  OPTcrossref =  {},
  OPTkey = 	 {},
  OPTpages = 	 {},
  OPTpublisher = {},
  OPTyear = 	 {},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTtype = 	 {},
  OPTchapter = 	 {},
  OPTaddress = 	 {},
  OPTedition = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@InCollection{libsvmbionlp04a,
  author = 	 {Jose C. Clemente and Kentaro Torisawa and Kenji Satou
},
  title = 	 {Improving the Identification of Non-Anaphoric it using Support Vector Machines
},
  booktitle = 	 {International Joint Workshop on Natural Language Processing in Biomedicine and its Applications (NLPBA/BioNLP 2004), Geneva, Switzerland},
  OPTcrossref =  {},
  OPTkey = 	 {},
  OPTpages = 	 {},
  OPTpublisher = {},
  year =	 {August 2004},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTtype = 	 {},
  OPTchapter = 	 {},
  OPTaddress = 	 {},
  OPTedition = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}



@InCollection{libsvmkdd02a,
url={http://www.smeal.psu.edu/ebrc/publications/res_papers/2002_17.pdf},
  author = 	 {Secil Ugurel
and Robert Krovetz
and C. Lee Giles
and David M. Pennock
and Eric Glover
and Hongyuan Zha},
  title = 	 {What is the code? Automatic Classification of Source Code Archives},
  booktitle = 	 {ACM KDD},
  OPTcrossref =  {},
  OPTkey = 	 {},
  OPTpages = 	 {},
  OPTpublisher = {},
  year =	 {2002},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTtype = 	 {},
  OPTchapter = 	 {},
  OPTaddress = 	 {},
  OPTedition = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@InCollection{libsvmcec04a,
url={http://www-ra.informatik.uni-tuebingen.de/publikationen/2004/ulmer04evolution.pdf},
  author = 	 {    Holger Ulmer, Felix Streichert, and Andreas Zell
},
  title = 	 {Evolution Strategies with Controlled Model Assistance
},
  booktitle = 	 {    Congress on Evolutionary Computation (CEC 2004)
},
  OPTcrossref =  {},
  OPTkey = 	 {},
  pages =	 {569--1576},
  publisher =	 {IEEE Press},
  OPTyear = 	 {},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTtype = 	 {},
  OPTchapter = 	 {},
  OPTaddress = 	 {},
  OPTedition = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}

@InCollection{libsvmidamp03a,
url={http://www.ailab.si/idamap/idamap2003/Curk.pdf},
  author = 	 {T Curk and B Zupan and U Petrovic and J Demsar and G Shaulsky and L Sacchi and C Larizza and R Bellazzi},
  title = 	 {Machine Learning for Functional Genomics: Some Experiments with Supervised Learning on Microarray Data Set},
  booktitle = 	 {IDAMP},
  OPTcrossref =  {},
  OPTkey = 	 {},
  OPTpages = 	 {},
  OPTpublisher = {},
  year =	 {2003},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTtype = 	 {},
  OPTchapter = 	 {},
  OPTaddress = 	 {},
  OPTedition = 	 {},
  OPTmonth = 	 {},
  OPTnote = 	 {},
  OPTannote = 	 {}
}