mlpaper.bib

@BOOK{HastieBook:SL,
  author = {T.~Hastie and R.~Tishirani and J.~Friedman},
  title = {The Elements of Statistical Learning: Data Mining, Inference, and Prediction},
  publisher = {Springer-Verlag},
  year = {2001},
  address=       {New York}
}

@BOOK{Vapnik:1998,
  author =       {V. Vapnik},
  title =        {Statistical Learning Theory},
  publisher =    {John Wiley and Sons},
  year =         {1998},
  volume =       {},
  series =       {},
  address =      {New York},
  edition =      {}
}

@book{wasserman2004all,
  title={All of statistics: a concise course in statistical inference},
  author={Wasserman, L.},
  year={2004},
  publisher={Springer Verlag}
}
@book{motwani2010randomized,
  title={Randomized algorithms},
  author={Motwani, R. and Raghavan, P.},
  year={2010},
  publisher={Chapman \& Hall/CRC}
}
@article{lange1995gradient,
  title={A gradient algorithm locally equivalent to the EM algorithm},
  author={Lange, K.},
  journal={Journal of the Royal Statistical Society. Series B (Methodological)},
  pages={425--437},
  year={1995},
  publisher={JSTOR}
}
@article{dempster1977maximum,
  title={Maximum likelihood from incomplete data via the EM algorithm},
  author={Dempster, A.P. and Laird, N.M. and Rubin, D.B.},
  journal={Journal of the Royal Statistical Society. Series B (Methodological)},
  pages={1--38},
  year={1977},
  publisher={JSTOR}
}
@article{bergstra2011algorithms,
  title={Algorithms for hyper-parameter optimization},
  author={Bergstra, J. and Bardenet, R. and Bengio, Y. and K{\'e}gl, B. and others},
  year={2011}
}
@inproceedings{martins2011augmented,
  title={An augmented lagrangian approach to constrained map inference},
  author={Martins, A.F.T. and Figueiredo, M.A.T. and Aguiar, P.M.Q. and Smith, N.A. and Xing, E.P.},
  booktitle={International Conference on Machine Learning},
  year={2011}
}
@article{cesa2011efficient,
  title={Efficient online learning via randomized rounding},
  author={Cesa-Bianchi, N. and Shamir, O.},
  journal={Arxiv preprint arXiv:1106.2429},
  year={2011}
}
@inproceedings{hazanbeating,
  title={Beating SGD: Learning SVMs in Sublinear Time},
  author={Hazan, E. and Koren, T. and Srebro, N.},
  booktitle={Advances in Neural Information Processing Systems},
  year={2011}
}
@inproceedings{shalev2007pegasos,
  title={Pegasos: Primal estimated sub-gradient solver for svm},
  author={Shalev-Shwartz, S. and Singer, Y. and Srebro, N.},
  booktitle={Proceedings of the 24th international conference on Machine learning},
  pages={807--814},
  year={2007},
  organization={ACM}
}
@article{cotter2011better,
  title={Better mini-batch algorithms via accelerated gradient methods},
  author={Cotter, A. and Shamir, O. and Srebro, N. and Sridharan, K.},
  journal={Arxiv preprint arXiv:1106.4574},
  year={2011}
}
@article{menon2009large,
  title={Large-scale support vector machines: algorithms and theory},
  author={Menon, A.K.},
  journal={Research Exam, University of California, San Diego},
  year={2009}
}
@article{arora2005multiplicative,
  title={The multiplicative weights update method: a meta algorithm and applications},
  author={Arora, S. and Hazan, E. and Kale, S.},
  journal={Manuscript, 2005. Preliminary draft of paper available online at http://www.cs.princeton.edu/~arora/pubs/MWsurvey.pdf},
  year={2005},
  publisher={Citeseer}
}
@article{nesterov2009primal,
  title={Primal-dual subgradient methods for convex problems},
  author={Nesterov, Y.},
  journal={Mathematical programming},
  volume={120},
  number={1},
  pages={221--259},
  year={2009},
  publisher={Springer}
}
@article{hazan2009survey,
  title={A survey: The convex optimization approach to regret minimization},
  author={Hazan, E.},
  year={2009},
  publisher={Citeseer}
}
@article{mahoney2011randomized,
  title={Randomized algorithms for matrices and data},
  author={Mahoney, M.W.},
  journal={Arxiv preprint arXiv:1104.5557},
  year={2011}
}
@article{keerthi2006modified,
  title={A modified finite Newton method for fast solution of large scale linear SVMs},
  author={Keerthi, S.S. and DeCoste, D.},
  journal={Journal of Machine Learning Research},
  volume={6},
  number={1},
  pages={341},
  year={2006},
  publisher={Citeseer}
}
@article{shi2008fast,
  title={A Fast Hybrid Algorithm for Large Scale l1-Regularized Logistic Regression},
  author={Shi, J. and Yin, W. and Osher, S. and Sajda, P.},
  journal={Journal of Machine Learning Research},
  volume={1},
  pages={8888},
  year={2008}
}
@article{bach2011convex,
  title={Convex optimization with sparsity-inducing norms},
  author={Bach, F. and Jenatton, R. and Mairal, J. and Obozinski, G.},
  journal={Optimization for Machine Learning},
  pages={19--54},
  year={2011},
  publisher={MIT Press}
}
@article{balakrishnan2008algorithms,
  title={Algorithms for sparse linear classifiers in the massive data setting},
  author={Balakrishnan, S. and Madigan, D.},
  journal={The Journal of Machine Learning Research},
  volume={9},
  pages={313--337},
  year={2008},
  publisher={JMLR. org}
}
@article{xiao2010dual,
  title={Dual averaging methods for regularized stochastic learning and online optimization},
  author={Xiao, L.},
  journal={The Journal of Machine Learning Research},
  volume={11},
  pages={2543--2596},
  year={2010},
  publisher={JMLR. org}
}
@inproceedings{shalev2009stochastic,
  title={Stochastic methods for l 1 regularized loss minimization},
  author={Shalev-Shwartz, S. and Tewari, A.},
  booktitle={Proceedings of the 26th Annual International Conference on Machine Learning},
  pages={929--936},
  year={2009},
  organization={ACM}
}
@inproceedings{clarkson2010sublinear,
  title={Sublinear Optimization for Machine Learning},
  author={Clarkson, K.L. and Hazan, E. and Woodruff, D.P.},
  booktitle={Proceedings of the 2010 IEEE 51st Annual Symposium on Foundations of Computer Science},
  pages={449--457},
  year={2010},
  organization={IEEE Computer Society}
}
@article{kapoor2005learning,
  title={Learning and classifying under hard budgets},
  author={Kapoor, A. and Greiner, R.},
  journal={Machine Learning: ECML 2005},
  pages={170--181},
  year={2005},
  publisher={Springer}
}
@article{genkin2007large,
  title={Large-scale Bayesian logistic regression for text categorization},
  author={Genkin, A. and Lewis, D.D. and Madigan, D.},
  journal={Technometrics},
  volume={49},
  number={3},
  pages={291--304},
  year={2007},
  publisher={ASA}
}
@article{tibshirani1996regression,
  title={Regression shrinkage and selection via the lasso},
  author={Tibshirani, R.},
  journal={Journal of the Royal Statistical Society. Series B (Methodological)},
  pages={267--288},
  year={1996},
  publisher={JSTOR}
}
@article{cotter2012kernelized,
  title={The Kernelized Stochastic Batch Perceptron},
  author={Cotter, A. and Shalev-Shwartz, S. and Srebro, N.},
  journal={Arxiv preprint arXiv:1204.0566},
  year={2012}
}

@article{sdp2007,
  title={On Analyzing Semidefinite Programming Relaxations of Complex Quadratic Optimization Problems},
  author={J.~Zhang and Y.~Ye  and A. M.-C.~So},
  journal={Handbook of approximation algorithms and metaheurististics},
  volume={10},
  year={2007},
  publisher={Chapman \& Hall}
}
@article{hazan2011optimal,
  title={Optimal algorithms for ridge and Lasso regression with partially observed attributes},
  author={Hazan, E. and Koren, T.},
  journal={Arxiv preprint arXiv:1108.4559},
  year={2011}
}
@inproceedings{zhang2004solving,
  title={Solving large scale linear prediction problems using stochastic gradient descent algorithms},
  author={Zhang, T.},
  booktitle={Proceedings of the twenty-first international conference on Machine learning},
  pages={116},
  year={2004},
  organization={ACM}
}
@article{xiao2010dual,
  title={Dual averaging methods for regularized stochastic learning and online optimization},
  author={Xiao, L.},
  journal={The Journal of Machine Learning Research},
  volume={11},
  pages={2543--2596},
  year={2010},
  publisher={JMLR. org}
}
@inproceedings{panda1995global,
  title={Global reduction in wormhole k-ary n-cube networks with multidestination exchange worms},
  author={Panda, D.K.},
  booktitle={In IPPS: 9th International Parallel Processing Symposium},
  pages={652--659},
  year={1995},
  organization={IEEE Computer Society Press}
}
@article{tsumoto2004mining,
  title={Mining diagnostic rules from clinical databases using rough sets and medical diagnostic model},
  author={Tsumoto, S.},
  journal={Information sciences},
  volume={162},
  number={2},
  pages={65--80},
  year={2004},
  publisher={Elsevier}
}
@inproceedings{garberapproximating,
  title={Approximating Semidefinite Programs in Sublinear Time},
  author={Garber, D. and Hazan, E.},
  booktitle={Advances in Neural Information Processing Systems},
  year={2011}
}
@inproceedings{hogan1990livermore,
  title={The Livermore distributed storage system: Requirements and overview},
  author={Hogan, C. and Cassell, L. and Foglesong, J. and Kordas, J. and Nemanic, M. and Richmond, G.},
  booktitle={Digest of Papers. Tenth IEEE Symposium on Mass Storage Systems},
  pages={6--17},
  year={1990},
  organization={IEEE}
}
@article{guyon2004result,
  title={Result analysis of the nips 2003 feature selection challenge},
  author={Guyon, I. and Gunn, S. and Ben-Hur, A. and Dror, G.},
  journal={Advances in Neural Information Processing Systems},
  volume={17},
  pages={545--552},
  year={2004},
  publisher={Citeseer}
}
@inproceedings{DelanyFLAIRS06,
  AUTHOR =       "S. J. Delany and P. Cunningham and A. Tsymbal",
  TITLE =        "A Comparison of Ensemble and Case-base Maintenance Techniques for handling Concept Drift in Spam Filtering",
  BOOKTITLE =    "Proceedings of the 19th International Conference on Artificial Intelligence (FLAIRS 2006)",
  YEAR =         "2006",
  editor = 	"G. Sutcliffe and R. Goebel",
    pages = 	 "340--345",
    publisher="AAAI Press",
}
@article{DelanyKBS05,
  author = "S. J. Delany and P. Cunningham and A. Tsymbal and L. Coyle",
  title = "A Case-Based Technique for Tracking Concept Drift in Spam Filtering",
  journal= "Knowledge-Based Systems",
  volume = {18},
  number = {4--5},
  pages = {187--195},
  publisher = "Elsevier",
  year = "2005"
}
@inproceedings{kohavi1995study,
  title={A study of cross-validation and bootstrap for accuracy estimation and model selection},
  author={Kohavi, R.},
  booktitle={International joint Conference on artificial intelligence},
  volume={14},
  pages={1137--1145},
  year={1995},
  organization={LAWRENCE ERLBAUM ASSOCIATES LTD}
}
@article{page1999pagerank,
  title={The PageRank citation ranking: bringing order to the web.},
  author={Page, Lawrence and Brin, Sergey and Motwani, Rajeev and Winograd, Terry},
  year={1999},
  publisher={Stanford InfoLab}
}
@article{androutsopoulos2000evaluation,
  title={An evaluation of naive bayesian anti-spam filtering},
  author={Androutsopoulos, Ion and Koutsias, John and Chandrinos, Konstantinos V and Paliouras, George and Spyropoulos, Constantine D},
  journal={arXiv preprint cs/0006013},
  year={2000}
}
@book{white2012hadoop,
  title={Hadoop: The definitive guide},
  author={White, Tom},
  year={2012},
  publisher={O'Reilly Media, Inc.}
}
@article{mahoutscalable,
  title={Scalable machine-learning and data-mining library},
  author={Mahout, Apache},
  journal={available at mahout. apache. org}
}
@inproceedings{zaharia2010spark,
  title={Spark: cluster computing with working sets},
  author={Zaharia, Matei and Chowdhury, Mosharaf and Franklin, Michael J and Shenker, Scott and Stoica, Ion},
  booktitle={Proceedings of the 2nd USENIX conference on Hot topics in cloud computing},
  pages={10--10},
  year={2010}
}
@article{borthakur2008hdfs,
  title={HDFS architecture guide},
  author={Borthakur, Dhruba},
  journal={Hadoop Apache Project. http://hadoop. apache. org/common/docs/current/hdfs\_design. pdf},
  year={2008}
}
@article{dean2008mapreduce,
  title={MapReduce: simplified data processing on large clusters},
  author={Dean, Jeffrey and Ghemawat, Sanjay},
  journal={Communications of the ACM},
  volume={51},
  number={1},
  pages={107--113},
  year={2008},
  publisher={ACM}
}
@book{gropp1999using,
  title={Using MPI-: Portable Parallel Programming with the Message Passing Interface},
  author={Gropp, William and Lusk, Ewing L and Skjellum, Anthony},
  volume={1},
  year={1999},
  publisher={MIT press}
}
@incollection{peng2012sublinear,
  title={Sublinear algorithms for penalized logistic regression in massive datasets},
  author={Peng, Haoruo and Wang, Zhengyu and Chang, Edward Y and Zhou, Shuchang and Zhang, Zhihua},
  booktitle={Machine Learning and Knowledge Discovery in Databases},
  pages={553--568},
  year={2012},
  publisher={Springer}
}
@inproceedings{ma2009identifying,
  title={Identifying suspicious URLs: an application of large-scale online learning},
  author={Ma, Justin and Saul, Lawrence K and Savage, Stefan and Voelker, Geoffrey M},
  booktitle={Proceedings of the 26th Annual International Conference on Machine Learning},
  pages={681--688},
  year={2009},
  organization={ACM}
}
@article{chang2011psvm,
  title={Psvm: Parallelizing support vector machines on distributed computers},
  author={Chang, Edward Y and Zhu, Kaihua and Wang, Hao and Bai, Hongjie and Li, Jian and Qiu, Zhihuan and Cui, Hang },
  journal={Advances in Neural Information Processing Systems},
  Volume={20},
  pages={213--230},
  year={2007},
  publisher={Citeseer}
}
@article{Liu:2011:PPL:1961189.1961198,
  author = {Liu, Zhiyuan and Zhang, Yuzhou and Chang, Edward Y. and Sun, Maosong},
  title = {PLDA+: Parallel latent dirichlet allocation with data placement and pipeline processing},
  journal = {ACM Trans. Intell. Syst. Technol.},
  issue_date = {April 2011},
  volume = {2},
  number = {3},
  month = may,
  year = {2011},
  issn = {2157-6904},
  pages = {26:1--26:18},
  articleno = {26},
  numpages = {18},
  url = {http://doi.acm.org/10.1145/1961189.1961198},
  doi = {10.1145/1961189.1961198},
  acmid = {1961198},
  publisher = {ACM},
  address = {New York, NY, USA},
  keywords = {Gibbs sampling, Topic models, distributed parallel computations, latent Dirichlet allocation},
}
@article{le2011building,
  title={Building high-level features using large scale unsupervised learning},
  author={Le, Quoc V and Ranzato, Marc'Aurelio and Monga, Rajat and Devin, Matthieu and Chen, Kai and Corrado, Greg S and Dean, Jeff and Ng, Andrew Y},
  journal={arXiv preprint arXiv:1112.6209},
  year={2011}
}
@inproceedings{kyrola2012graphchi,
  title={GraphChi: Large-scale graph computation on just a PC},
  author={Kyrola, Aapo and Blelloch, Guy and Guestrin, Carlos},
  booktitle={Proceedings of the 10th conference on Symposium on Opearting Systems Design \& Implementation},
  year={2012}
}
@incollection{peng2012sublinear,
  title={Sublinear algorithms for penalized logistic regression in massive datasets},
  author={Peng, Haoruo and Wang, Zhengyu and Chang, Edward Y and Zhou, Shuchang and Zhang, Zhihua},
  booktitle={Machine Learning and Knowledge Discovery in Databases},
  pages={553--568},
  year={2012},
  publisher={Springer}
}
@article{fan2008liblinear,
  title={LIBLINEAR: A library for large linear classification},
  author={Fan, Rong-En and Chang, Kai-Wei and Hsieh, Cho-Jui and Wang, Xiang-Rui and Lin, Chih-Jen},
  journal={The Journal of Machine Learning Research},
  volume={9},
  pages={1871--1874},
  year={2008},
  publisher={JMLR. org}
}
@article{lewis2008tastes,
  title={Tastes, ties, and time: A new social network dataset using Facebook. com},
  author={Lewis, Kevin and Kaufman, Jason and Gonzalez, Marco and Wimmer, Andreas and Christakis, Nicholas},
  journal={Social Networks},
  volume={30},
  number={4},
  pages={330--342},
  year={2008},
  publisher={Elsevier}
}
@article{lewis2004rcv1,
  title={Rcv1: A new benchmark collection for text categorization research},
  author={Lewis, David D and Yang, Yiming and Rose, Tony G and Li, Fan},
  journal={The Journal of Machine Learning Research},
  volume={5},
  pages={361--397},
  year={2004},
  publisher={JMLR. org}
}
@article{subhlok1993exploiting,
  title={Exploiting task and data parallelism on a multicomputer},
  author={Subhlok, Jaspal and Stichnoth, James M and O'hallaron, David R and Gross, Thomas},
  journal={ACM SIGPLAN Notices},
  volume={28},
  number={7},
  pages={13--22},
  year={1993},
  publisher={ACM}
}
@inproceedings{sarwar2001item,
  title={Item-based collaborative filtering recommendation algorithms},
  author={Sarwar, Badrul and Karypis, George and Konstan, Joseph and Riedl, John},
  booktitle={Proceedings of the 10th international conference on World Wide Web},
  pages={285--295},
  year={2001},
  organization={ACM}
}
@book{chang2011foundations,
  title={Foundations of Large-Scale Multimedia Information Management and Retrieval},
  author={Chang, Edward Y},
  year={2011},
  publisher={Springerverlag Berlin Heidelberg and Tsinghua University Press}
}
@book{Bekkerman2012,
  title={Scaling Up Machine Learning},
  author={Bekkerman, Ron and Bilenko, Mikhail and Langford, John},
  year={2012},
  publisher={Cambridge University Press}
}
@article{newman2007distributed,
  title={Distributed inference for latent dirichlet allocation},
  author={Newman, David and Asuncion, Arthur and Smyth, Padhraic and Welling, Max},
  journal={Advances in neural information processing systems},
  volume={20},
  number={1081-1088},
  pages={17--24},
  year={2007}
}
@ARTICLE{Chen5444877, 
author={Wen-Yen Chen and Yangqiu Song and Hongjie Bai and Chih-Jen Lin and Chang, E.Y.}, 
journal={Pattern Analysis and Machine Intelligence, IEEE Transactions on}, 
title={Parallel Spectral Clustering in Distributed Systems}, 
year={2011}, 
volume={33}, 
number={3}, 
pages={568-586}
}
@inproceedings{Li:2008:PPF:1454008.1454027,
 author = {Li, Haoyuan and Wang, Yi and Zhang, Dong and Zhang, Ming and Chang, Edward Y.},
 title = {Pfp: parallel fp-growth for query recommendation},
 booktitle = {Proceedings of the 2008 ACM conference on Recommender systems},
 series = {RecSys '08},
 year = {2008},
 isbn = {978-1-60558-093-7},
 location = {Lausanne, Switzerland},
 pages = {107--114},
 numpages = {8},
 publisher = {ACM},
 }