Daniel Hsu

Assistant professor
Computer Science Department and Data Science Institute
Columbia University

E-mail: <username>@cs.columbia.edu
Office: 426 Mudd, +1 ???-???-????

Biographical sketch.

Information for prospective students.

Research papers

[ expand all, collapse all ] Many articles also available on arXiv.

Coding with asymmetric prior knowledge.
Alexandr Andoni, Javad Ghaderi, Daniel Hsu, Dan Rubenstein, Omri Weinstein.
Preprint, 2017.
[ external link copy bib download bib ]
@article{andoni2017coding,
  author = "Andoni, Alexandr and Ghaderi, Javad and Hsu, Daniel and Rubenstein, Dan and Weinstein, Omri",
  journal = "arXiv preprint arXiv:1707.04875",
  title = "Coding with asymmetric prior knowledge",
  year = "2017"
}
Parameter identification in Markov chain choice models.
Arushi Gupta, Daniel Hsu.
Preprint, 2017.
[ external link copy bib download bib ]
@article{gupta2017parameter,
  author = "Gupta, Arushi and Hsu, Daniel",
  journal = "arXiv preprint arXiv:1706.00729",
  title = "Parameter identification in Markov chain choice models",
  year = "2017"
}
Linear regression without correspondence.
Daniel Hsu, Kevin Shi, Xiaorui Sun.
Preprint, 2017.
[ external link copy bib download bib ]
@article{gupta2017parameter,
  author = "Hsu, Daniel and Shi, Kevin and Sun, Xiaorui",
  journal = "arXiv preprint arXiv:1705.07048",
  title = "Linear regression without correspondence",
  year = "2017"
}
Greedy approaches to symmetric orthogonal tensor decomposition.
Cun Mu, Daniel Hsu, Donald Goldfarb.
Preprint, 2017.
[ external link copy bib download bib ]
@article{mu2017greedy,
  author = "Mu, Cun and Hsu, Daniel and Goldfarb, Donald",
  journal = "arXiv preprint arXiv:1706.01169",
  title = "Greedy approaches to symmetric orthogonal tensor decomposition",
  year = "2017"
}
Greedy bi-criteria approximations for \(k\)-medians and \(k\)-means.
Daniel Hsu, Matus Telgarsky.
Preprint, 2016.
[ external link copy bib download bib ]
@article{hsu2016greedy,
  author = "Hsu, Daniel and Telgarsky, Matus",
  journal = "arXiv preprint arXiv:1607.06203",
  title = "Greedy bi-criteria approximations for k-medians and k-means",
  year = "2016"
}
Kernel ridge vs. principal component regression: minimax bounds and the qualification of regularization operators.
Lee H. Dicker, Dean P. Foster, Daniel Hsu.
Electronic Journal of Statistics, 1(1):1022–1047, 2017.
[ local pdf file ejs link copy bib download bib ]
@article{dicker2017kernel,
  author = "Dicker, Lee H. and Foster, Dean P. and Hsu, Daniel",
  journal = "Electronic Journal of Statistics",
  number = "1",
  pages = "1022--1047",
  title = "Kernel ridge vs. principal component regression: minimax bounds and the qualification of regularization operators",
  volume = "1",
  year = "2017"
}
FairTest: discovering unwarranted associations in data-driven applications.
Florian Tramer, Vaggelis Atlidakis, Roxana Geambasu, Daniel Hsu, Jean-Pierre Hubaux, Mathias Humbert, Ari Juels, Huang Lin.
In Second IEEE European Symposium on Security and Privacy. 2017.
[ external link slides from privacycon copy bib download bib ]
@inproceedings{tramer2017fairtest,
  author = "Tramer, Florian and Atlidakis, Vaggelis and Geambasu, Roxana and Hsu, Daniel and Hubaux, Jean-Pierre and Humbert, Mathias and Juels, Ari and Lin, Huang",
  booktitle = "Second IEEE European Symposium on Security and Privacy",
  title = "FairTest: discovering unwarranted associations in data-driven applications",
  year = "2017"
}
Correspondence retrieval.
Alexandr Andoni, Daniel Hsu, Kevin Shi, Xiaorui Sun.
In Thirtieth Annual Conference on Learning Theory. 2017.
[ local pdf file pmlr link copy bib download bib ]
@inproceedings{andoni2017correspondence,
  author = "Andoni, Alexandr and Hsu, Daniel and Shi, Kevin and Sun, Xiaorui",
  booktitle = "Thirtieth Annual Conference on Learning Theory",
  title = "Correspondence retrieval",
  year = "2017"
}
Unsupervised part-of-speech tagging with anchor hidden Markov models.
Karl Stratos, Michael Collins, Daniel Hsu.
Transactions of the Association for Computational Linguistics, 4:245–257, 2016.
[ external link copy bib download bib ]
@article{stratos2016unsupervised,
  author = "Stratos, Karl and Collins, Michael and Hsu, Daniel",
  journal = "Transactions of the Association for Computational Linguistics",
  pages = "245--257",
  title = "Unsupervised part-of-speech tagging with anchor hidden Markov models",
  volume = "4",
  year = "2016"
}
Loss minimization and parameter estimation with heavy tails.
Daniel Hsu, Sivan Sabato.
Journal of Machine Learning Research, 17(18):1–40, 2016.
[ external link slides for related talk copy bib download bib ]
@article{hsu2016loss,
  author = "Hsu, Daniel and Sabato, Sivan",
  journal = "Journal of Machine Learning Research",
  number = "18",
  pages = "1--40",
  title = "Loss minimization and parameter estimation with heavy tails",
  volume = "17",
  year = "2016"
}
Global analysis of Expectation Maximization for mixtures of two Gaussians.
Ji Xu, Daniel Hsu, Arian Maleki.
In Advances in Neural Information Processing Systems 29. 2016.
[ local pdf file short version arxiv link copy bib download bib ]
@inproceedings{xu2016global,
  author = "Xu, Ji and Hsu, Daniel and Maleki, Arian",
  booktitle = "Advances in Neural Information Processing Systems 29",
  title = "Global analysis of Expectation Maximization for mixtures of two Gaussians",
  year = "2016"
}
Do dark matter halos explain lensing peaks?.
Jose Manuel Zorrilla Matilla, Zoltan Haiman, Daniel Hsu, Arushi Gupta, Andrea Petri.
Phys. Rev. D, 94:083506, Oct 2016.
[ external link aps link copy bib download bib ]
@article{zorrilla2016dark,
  author = "Zorrilla Matilla, Jose Manuel and Haiman, Zoltan and Hsu, Daniel and Gupta, Arushi and Petri, Andrea",
  issue = "8",
  journal = "Phys. Rev. D",
  month = "Oct",
  pages = "083506",
  title = "Do dark matter halos explain lensing peaks?",
  volume = "94",
  year = "2016"
}
Compact kernel models for acoustic modeling via random feature selection.
Avner May, Michael Collins, Daniel Hsu, Brian Kingsbury.
In Forty-First IEEE International Conference on Acoustics, Speech and Signal Processing. 2016.
[ external link copy bib download bib ]
@inproceedings{may2016compact,
  author = "May, Avner and Collins, Michael and Hsu, Daniel and Kingsbury, Brian",
  booktitle = "Forty-First IEEE International Conference on Acoustics, Speech and Signal Processing",
  title = "Compact kernel models for acoustic modeling via random feature selection",
  year = "2016"
}
When are overcomplete topic models identifiable?.
Anima Anandkumar, Daniel Hsu, Majid Janzamin, Sham M. Kakade.
Journal of Machine Learning Research, 16(Dec):2643–2694, 2015.
[ external link copy bib download bib ]
@article{anandkumar2015when,
  author = "Anandkumar, Anima and Hsu, Daniel and Janzamin, Majid and Kakade, Sham M.",
  journal = "Journal of Machine Learning Research",
  number = "Dec",
  pages = "2643--2694",
  title = "When are overcomplete topic models identifiable? Uniqueness of tensor Tucker decompositions with structured sparsity",
  volume = "16",
  year = "2015"
}
Sunlight: fine-grained targeting detection at scale with statistical confidence.
Mathias Lecuyer, Riley Spahn, Yannis Spiliopoulos, Augustin Chaintreau, Roxana Geambasu, Daniel Hsu.
In Twenty-Second ACM Conference on Computer and Communications Security. 2015.
[ local pdf file project website copy bib download bib ]
@inproceedings{lecuyer2015sunlight,
  author = "Lecuyer, Mathias and Spahn, Riley and Spiliopoulos, Yannis and Chaintreau, Augustin and Geambasu, Roxana and Hsu, Daniel",
  booktitle = "Twenty-Second ACM Conference on Computer and Communications Security",
  title = "Sunlight: fine-grained targeting detection at scale with statistical confidence",
  year = "2015"
}
Successive rank-one approximations for nearly orthogonally decomposable symmetric tensors.
Cun Mu, Daniel Hsu, Donald Goldfarb.
SIAM Journal on Matrix Analysis and Applications, 36(4):1638–1659, 2015.
[ external link siam link copy bib download bib ]
@article{mu2015successive,
  author = "Mu, Cun and Hsu, Daniel and Goldfarb, Donald",
  journal = "SIAM Journal on Matrix Analysis and Applications",
  number = "4",
  pages = "1638--1659",
  title = "Successive rank-one approximations for nearly orthogonally decomposable symmetric tensors",
  volume = "36",
  year = "2015"
}
A spectral algorithm for latent Dirichlet allocation.
Anima Anandkumar, Dean P. Foster, Daniel Hsu, Sham M. Kakade, Yi-Kai Liu.
Algorithmica, 72(1):193–214, 2015.
[ local pdf file springer link copy bib download bib ]
@article{anandkumar2015spectral,
  author = "Anandkumar, Anima and Foster, Dean P. and Hsu, Daniel and Kakade, Sham M. and Liu, Yi-Kai",
  journal = "Algorithmica",
  number = "1",
  pages = "193--214",
  title = "A spectral algorithm for latent Dirichlet allocation",
  volume = "72",
  year = "2015"
}
Model-based word embeddings from decompositions of count matrices.
Karl Stratos, Michael Collins, Daniel Hsu.
In Fifty-Third Annual Meeting of the Association for Computational Linguistics. 2015.
[ local pdf file acl link copy bib download bib ]
@inproceedings{stratos2015modelbased,
  author = "Stratos, Karl and Collins, Michael and Hsu, Daniel",
  booktitle = "Fifty-Third Annual Meeting of the Association for Computational Linguistics",
  title = "Model-based word embeddings from decompositions of count matrices",
  year = "2015"
}
Mixing time estimation in reversible Markov chains from a single sample path.
Daniel Hsu, Aryeh Kontorovich, Csaba Szepesvari.
In Advances in Neural Information Processing Systems 28. 2015.
[ external link talk slides copy bib download bib ]
@inproceedings{hsu2015mixing,
  author = "Hsu, Daniel and Kontorovich, Aryeh and Szepesvari, Csaba",
  booktitle = "Advances in Neural Information Processing Systems 28",
  title = "Mixing time estimation in reversible Markov chains from a single sample path",
  year = "2015"
}
Method of moments learning for left-to-right hidden Markov models.
Yusuf Cem Subakan, Johannes Traa, Paris Smaragdis, Daniel Hsu.
In IEEE Workshop on Applications of Signal Processing to Audio and Acoustics. 2015.
[ external link copy bib download bib ]
@inproceedings{subakan2015method,
  author = "Subakan, Yusuf Cem and Traa, Johannes and Smaragdis, Paris and Hsu, Daniel",
  booktitle = "IEEE Workshop on Applications of Signal Processing to Audio and Acoustics",
  title = "Method of moments learning for left-to-right hidden Markov models",
  year = "2015"
}
Learning sparse low-threshold linear classifiers.
Sivan Sabato, Shai Shalev-Shwartz, Nathan Srebro, Daniel Hsu, Tong Zhang.
Journal of Machine Learning Research, 16(Jul):1275–1304, 2015.
[ external link copy bib download bib ]
@article{sabato2015learning,
  author = "Sabato, Sivan and Shalev-Shwartz, Shai and Srebro, Nathan and Hsu, Daniel and Zhang, Tong",
  journal = "Journal of Machine Learning Research",
  number = "Jul",
  pages = "1275--1304",
  title = "Learning sparse low-threshold linear classifiers",
  volume = "16",
  year = "2015"
}
Efficient and parsimonious agnostic active learning.
Tzu-Kuo Huang, Alekh Agarwal, Daniel Hsu, John Langford, Robert E. Schapire.
In Advances in Neural Information Processing Systems 28. 2015.
[ external link copy bib download bib ]
@inproceedings{huang2015efficient,
  author = "Huang, Tzu-Kuo and Agarwal, Alekh and Hsu, Daniel and Langford, John and E. Schapire, Robert",
  booktitle = "Advances in Neural Information Processing Systems 28",
  title = "Efficient and parsimonious agnostic active learning",
  year = "2015"
}
Tensor decompositions for learning latent variable models.
Anima Anandkumar, Rong Ge, Daniel Hsu, Sham M. Kakade, Matus Telgarsky.
Journal of Machine Learning Research, 15(Aug):2773–2831, 2014.
[ local pdf file tutorial slides jmlr link copy bib download bib ]
@article{anandkumar2014tensor,
  author = "Anandkumar, Anima and Ge, Rong and Hsu, Daniel and Kakade, Sham M. and Telgarsky, Matus",
  journal = "Journal of Machine Learning Research",
  number = "Aug",
  pages = "2773--2831",
  title = "Tensor decompositions for learning latent variable models",
  volume = "15",
  year = "2014"
}
Taming the monster: a fast and simple algorithm for contextual bandits.
Alekh Agarwal, Daniel Hsu, Satyen Kale, John Langford, Lihong Li, Robert E. Schapire.
In Thirty-First International Conference on Machine Learning. 2014.
[ local pdf file talk slides arxiv link copy bib download bib ]
@inproceedings{agarwal2014taming,
  author = "Agarwal, Alekh and Hsu, Daniel and Kale, Satyen and Langford, John and Li, Lihong and Schapire, Robert E.",
  booktitle = "Thirty-First International Conference on Machine Learning",
  title = "Taming the monster: a fast and simple algorithm for contextual bandits",
  year = "2014"
}
A spectral algorithm for learning class-based \(n\)-gram models of natural language.
Karl Stratos, Do-kyum Kim, Michael Collins, Daniel Hsu.
In Thirtieth Conference on Uncertainty in Artificial Intelligence. 2014.
[ local pdf file auai link code by Karl more code by Karl copy bib download bib ]
@inproceedings{stratos2014spectral,
  author = "Stratos, Karl and Kim, Do-kyum and Collins, Michael and Hsu, Daniel",
  booktitle = "Thirtieth Conference on Uncertainty in Artificial Intelligence",
  title = "A spectral algorithm for learning class-based $n$-gram models of natural language",
  year = "2014"
}
Scalable nonlinear learning with adaptive polynomial expansions.
Alekh Agarwal, Alina Beygelzimer, Daniel Hsu, John Langford, Matus Telgarsky.
In Advances in Neural Information Processing Systems 27. 2014.
[ external link copy bib download bib ]
@inproceedings{agarwal2014scalable,
  author = "Agarwal, Alekh and Beygelzimer, Alina and Hsu, Daniel and Langford, John and Telgarsky, Matus",
  booktitle = "Advances in Neural Information Processing Systems 27",
  title = "Scalable nonlinear learning with adaptive polynomial expansions",
  year = "2014"
}
Random design analysis of ridge regression.
Daniel Hsu, Sham M. Kakade, Tong Zhang.
Foundations of Computational Mathematics, 14(3):569–600, 2014.
[ local pdf file springer link arxiv link copy bib download bib ]
@article{hsu2014random,
  author = "Hsu, Daniel and Kakade, Sham M. and Zhang, Tong",
  journal = "Foundations of Computational Mathematics",
  number = "3",
  pages = "569--600",
  title = "Random design analysis of ridge regression",
  volume = "14",
  year = "2014"
}
A tensor approach to learning mixed membership community models.
Anima Anandkumar, Rong Ge, Daniel Hsu, Sham M. Kakade.
Journal of Machine Learning Research, 15(Jun):2239–2312, 2014.
[ external link arxiv link copy bib download bib ]
@article{anandkumar2014mixed,
  author = "Anandkumar, Anima and Ge, Rong and Hsu, Daniel and Kakade, Sham M.",
  journal = "Journal of Machine Learning Research",
  number = "Jun",
  pages = "2239--2312",
  title = "A tensor approach to learning mixed membership community models",
  volume = "15",
  year = "2014"
}
The large margin mechanism for differentially private maximization.
Kamalika Chaudhuri, Daniel Hsu, Shuang Song.
In Advances in Neural Information Processing Systems 27. 2014.
[ external link copy bib download bib ]
@inproceedings{chaudhuri2014large,
  author = "Chaudhuri, Kamalika and Hsu, Daniel and Song, Shuang",
  booktitle = "Advances in Neural Information Processing Systems 27",
  title = "The large margin mechanism for differentially private maximization",
  year = "2014"
}
Heavy-tailed regression with a generalized median-of-means.
Daniel Hsu, Sivan Sabato.
In Thirty-First International Conference on Machine Learning. 2014.
[ external link arxiv link copy bib download bib ]
@inproceedings{hsu2014heavytailed,
  author = "Hsu, Daniel and Sabato, Sivan",
  booktitle = "Thirty-First International Conference on Machine Learning",
  title = "Heavy-tailed regression with a generalized median-of-means",
  year = "2014"
}
When are overcomplete topic models identifiable?.
Anima Anandkumar, Daniel Hsu, Majid Janzamin, Sham M. Kakade.
In Advances in Neural Information Processing Systems 26. 2013.
[ external link copy bib download bib ]
@inproceedings{anandkumar2013when,
  author = "Anandkumar, Anima and Hsu, Daniel and Janzamin, Majid and Kakade, Sham M.",
  booktitle = "Advances in Neural Information Processing Systems 26",
  title = "When are overcomplete topic models identifiable? Uniqueness of tensor Tucker decompositions with structured sparsity",
  year = "2013"
}
Stochastic convex optimization with bandit feedback.
Alekh Agarwal, Dean P. Foster, Daniel Hsu, Sham M. Kakade, Alexander Rakhlin.
SIAM Journal on Optimization, 23(1):213–240, 2013.
[ local pdf file arxiv link siam link copy bib download bib ]
@article{agarwal2013stochastic,
  author = "Agarwal, Alekh and Foster, Dean P. and Hsu, Daniel and Kakade, Sham M. and Rakhlin, Alexander",
  journal = "SIAM Journal on Optimization",
  number = "1",
  pages = "213--240",
  title = "Stochastic convex optimization with bandit feedback",
  volume = "23",
  year = "2013"
}
A tensor spectral approach to learning mixed membership community models.
Anima Anandkumar, Rong Ge, Daniel Hsu, Sham M. Kakade.
In Twenty-Sixth Annual Conference on Learning Theory. 2013.
[ external link journal version with better title arxiv link copy bib download bib ]
@inproceedings{anandkumar2013mixed,
  author = "Anandkumar, Anima and Ge, Rong and Hsu, Daniel and Kakade, Sham M.",
  booktitle = "Twenty-Sixth Annual Conference on Learning Theory",
  title = "A tensor spectral approach to learning mixed membership community models",
  year = "2013"
}
Learning mixtures of spherical Gaussians: moment methods and spectral decompositions.
Daniel Hsu, Sham M. Kakade.
In Fourth Innovations in Theoretical Computer Science. 2013.
[ local pdf file talk slides arxiv link copy bib download bib ]
@inproceedings{hsu2013learning,
  author = "Hsu, Daniel and Kakade, Sham M.",
  booktitle = "Fourth Innovations in Theoretical Computer Science",
  title = "Learning mixtures of spherical Gaussians: moment methods and spectral decompositions",
  year = "2013"
}
Contrastive learning using spectral methods.
James Zou, Daniel Hsu, David Parkes, Ryan P. Adams.
In Advances in Neural Information Processing Systems 26. 2013.
[ local pdf file copy bib download bib ]
@inproceedings{zou2013contrastive,
  author = "Zou, James and Hsu, Daniel and Parkes, David and Adams, Ryan P.",
  booktitle = "Advances in Neural Information Processing Systems 26",
  title = "Contrastive learning using spectral methods",
  year = "2013"
}
Tail inequalities for sums of random matrices that depend on the intrinsic dimension.
Daniel Hsu, Sham M. Kakade, Tong Zhang.
Electronic Communications in Probability, 17(14):1–13, 2012.
[ local pdf file errata ecp link note on matrix mult. another note on matrix mult. copy bib download bib ]
@article{hsu2012tail,
  author = "Hsu, Daniel and Kakade, Sham M. and Zhang, Tong",
  journal = "Electronic Communications in Probability",
  number = "14",
  pages = "1--13",
  title = "Tail inequalities for sums of random matrices that depend on the intrinsic dimension",
  volume = "17",
  year = "2012"
}
A spectral algorithm for learning hidden Markov models.
Daniel Hsu, Sham M. Kakade, Tong Zhang.
Journal of Computer and System Sciences, 78(5):1460–1480, 2012.
[ local pdf file errata jcss link arxiv link copy bib download bib ]
@article{hsu2012spectral,
  author = "Hsu, Daniel and Kakade, Sham M. and Zhang, Tong",
  journal = "Journal of Computer and System Sciences",
  number = "5",
  pages = "1460--1480",
  title = "A spectral algorithm for learning hidden Markov models",
  volume = "78",
  year = "2012"
}
Random design analysis of ridge regression.
Daniel Hsu, Sham M. Kakade, Tong Zhang.
In Twenty-Fifth Annual Conference on Learning Theory. 2012.
[ external link journal version arxiv link copy bib download bib ]
@inproceedings{hsu2012random,
  author = "Hsu, Daniel and Kakade, Sham M. and Zhang, Tong",
  booktitle = "Twenty-Fifth Annual Conference on Learning Theory",
  title = "Random design analysis of ridge regression",
  year = "2012"
}
A method of moments for mixture models and hidden Markov models.
Anima Anandkumar, Daniel Hsu, Sham M. Kakade.
In Twenty-Fifth Annual Conference on Learning Theory. 2012.
[ external link talk slides slides for related talk arxiv link copy bib download bib ]
@inproceedings{anandkumar2012method,
  author = "Anandkumar, Anima and Hsu, Daniel and Kakade, Sham M.",
  booktitle = "Twenty-Fifth Annual Conference on Learning Theory",
  title = "A method of moments for mixture models and hidden Markov models",
  year = "2012"
}
Learning mixtures of tree graphical models.
Anima Anandkumar, Daniel Hsu, Furong Huang, Sham M. Kakade.
In Advances in Neural Information Processing Systems 25. 2012.
[ external link copy bib download bib ]
@inproceedings{anandkumar2012learning,
  author = "Anandkumar, Anima and Hsu, Daniel and Huang, Furong and Kakade, Sham M.",
  booktitle = "Advances in Neural Information Processing Systems 25",
  title = "Learning mixtures of tree graphical models",
  year = "2012"
}
A tail inequality for quadratic forms of subgaussian random vectors.
Daniel Hsu, Sham M. Kakade, Tong Zhang.
Electronic Communications in Probability, 17(52):1–6, 2012.
[ local pdf file ecp link copy bib download bib ]
@article{hsu2012inequality,
  author = "Hsu, Daniel and Kakade, Sham M. and Zhang, Tong",
  journal = "Electronic Communications in Probability",
  number = "52",
  pages = "1--6",
  title = "A tail inequality for quadratic forms of subgaussian random vectors",
  volume = "17",
  year = "2012"
}
Identifiability and unmixing of latent parse trees.
Daniel Hsu, Sham M. Kakade, Percy Liang.
In Advances in Neural Information Processing Systems 25. 2012.
[ local pdf file arxiv link copy bib download bib ]
@inproceedings{hsu2012identifiability,
  author = "Hsu, Daniel and Kakade, Sham M. and Liang, Percy",
  booktitle = "Advances in Neural Information Processing Systems 25",
  title = "Identifiability and unmixing of latent parse trees",
  year = "2012"
}
Convergence rates for differentially private statistical estimation.
Kamalika Chaudhuri, Daniel Hsu.
In Twenty-Ninth International Conference on Machine Learning. 2012.
[ local pdf file copy bib download bib ]
@inproceedings{chaudhuri2012convergence,
  author = "Chaudhuri, Kamalika and Hsu, Daniel",
  booktitle = "Twenty-Ninth International Conference on Machine Learning",
  title = "Convergence rates for differentially private statistical estimation",
  year = "2012"
}
Stochastic convex optimization with bandit feedback.
Alekh Agarwal, Dean P. Foster, Daniel Hsu, Sham M. Kakade, Alexander Rakhlin.
In Advances in Neural Information Processing Systems 24. 2011.
[ external link journal version siam link copy bib download bib ]
@inproceedings{agarwal2011stochastic,
  author = "Agarwal, Alekh and Foster, Dean P. and Hsu, Daniel and Kakade, Sham M. and Rakhlin, Alexander",
  booktitle = "Advances in Neural Information Processing Systems 24",
  title = "Stochastic convex optimization with bandit feedback",
  year = "2011"
}
Spectral methods for learning multivariate latent tree structure.
Anima Anandkumar, Kamalika Chaudhuri, Daniel Hsu, Sham M. Kakade, Le Song, Tong Zhang.
In Advances in Neural Information Processing Systems 24. 2011.
[ local pdf file arxiv link copy bib download bib ]
@inproceedings{anandkumar2011spectral,
  author = "Anandkumar, Anima and Chaudhuri, Kamalika and Hsu, Daniel and Kakade, Sham M. and Song, Le and Zhang, Tong",
  booktitle = "Advances in Neural Information Processing Systems 24",
  title = "Spectral methods for learning multivariate latent tree structure",
  year = "2011"
}
Sample complexity bounds for differentially private learning.
Kamalika Chaudhuri, Daniel Hsu.
In Twenty-Fourth Annual Conference on Learning Theory. 2011.
[ local pdf file pmlr link copy bib download bib ]
@inproceedings{chaudhuri2011sample,
  author = "Chaudhuri, Kamalika and Hsu, Daniel",
  booktitle = "Twenty-Fourth Annual Conference on Learning Theory",
  title = "Sample complexity bounds for differentially private learning",
  year = "2011"
}
Robust matrix decomposition with sparse corruptions.
Daniel Hsu, Sham M. Kakade, Tong Zhang.
IEEE Transactions on Information Theory, 57(11):7221–7234, 2011.
[ local pdf file arxiv link ieee link copy bib download bib ]
@article{hsu2011robust,
  author = "Hsu, Daniel and Kakade, Sham M. and Zhang, Tong",
  journal = "IEEE Transactions on Information Theory",
  number = "11",
  pages = "7221--7234",
  title = "Robust matrix decomposition with sparse corruptions",
  volume = "57",
  year = "2011"
}
Efficient optimal learning for contextual bandits.
Miroslav Dudik, Daniel Hsu, Satyen Kale, Nikos Karampatziakis, John Langford, Lev Reyzin, Tong Zhang.
In Twenty-Seventh Conference on Uncertainty in Artificial Intelligence. 2011.
[ local pdf file copy bib download bib ]
@inproceedings{dudik2011efficient,
  author = "Dudik, Miroslav and Hsu, Daniel and Kale, Satyen and Karampatziakis, Nikos and Langford, John and Reyzin, Lev and Zhang, Tong",
  booktitle = "Twenty-Seventh Conference on Uncertainty in Artificial Intelligence",
  title = "Efficient optimal learning for contextual bandits",
  year = "2011"
}
Algorithms for active learning.
Daniel Hsu.
Ph.D. dissertation, UC San Diego. 2010.
[ local pdf file copy bib download bib ]
@phdthesis{hsu2010algorithms,
  author = "Hsu, Daniel",
  school = "University of California, San Diego",
  title = "Algorithms for active learning",
  year = "2010"
}
An online learning-based framework for tracking.
Kamalika Chaudhuri, Yoav Freund, Daniel Hsu.
In Twenty-Sixth Conference on Uncertainty in Artificial Intelligence. 2010.
[ external link copy bib download bib ]
@inproceedings{chaudhuri2010online,
  author = "Chaudhuri, Kamalika and Freund, Yoav and Hsu, Daniel",
  booktitle = "Twenty-Sixth Conference on Uncertainty in Artificial Intelligence",
  title = "An online learning-based framework for tracking",
  year = "2010"
}
Agnostic active learning without constraints.
Alina Beygelzimer, Daniel Hsu, John Langford, Tong Zhang.
In Advances in Neural Information Processing Systems 23. 2010.
[ local pdf file arxiv link copy bib download bib ]
@inproceedings{beygelzimer2010agnostic,
  author = "Beygelzimer, Alina and Hsu, Daniel and Langford, John and Zhang, Tong",
  booktitle = "Advances in Neural Information Processing Systems 23",
  title = "Agnostic active learning without constraints",
  year = "2010"
}
A spectral algorithm for learning hidden Markov models.
Daniel Hsu, Sham M. Kakade, Tong Zhang.
In Twenty-Second Annual Conference on Learning Theory. 2009.
[ external link journal version errata copy bib download bib ]
@inproceedings{hsu2009spectral,
  author = "Hsu, Daniel and Kakade, Sham M. and Zhang, Tong",
  booktitle = "Twenty-Second Annual Conference on Learning Theory",
  title = "A spectral algorithm for learning hidden Markov models",
  year = "2009"
}
A parameter-free hedging algorithm.
Kamalika Chaudhuri, Yoav Freund, Daniel Hsu.
In Advances in Neural Information Processing Systems 22. 2009.
[ local pdf file note about \(\epsilon\)-quantile regret copy bib download bib ]
@inproceedings{chaudhuri2009parameterfree,
  author = "Chaudhuri, Kamalika and Freund, Yoav and Hsu, Daniel",
  booktitle = "Advances in Neural Information Processing Systems 22",
  title = "A parameter-free hedging algorithm",
  year = "2009"
}
Multi-label prediction via compressed sensing.
Daniel Hsu, Sham M. Kakade, John Langford, Tong Zhang.
In Advances in Neural Information Processing Systems 22. 2009.
[ local pdf file talk slides arxiv link copy bib download bib ]
@inproceedings{hsu2009multilabel,
  author = "Hsu, Daniel and Kakade, Sham M. and Langford, John and Zhang, Tong",
  booktitle = "Advances in Neural Information Processing Systems 22",
  title = "Multi-label prediction via compressed sensing",
  year = "2009"
}
Hierarchical sampling for active learning.
Sanjoy Dasgupta, Daniel Hsu.
In Twenty-Fifth International Conference on Machine Learning. 2008.
[ local pdf file copy bib download bib ]
@inproceedings{dasgupta2008hierarchical,
  author = "Dasgupta, Sanjoy and Hsu, Daniel",
  booktitle = "Twenty-Fifth International Conference on Machine Learning",
  title = "Hierarchical sampling for active learning",
  year = "2008"
}
On-line estimation with the multivariate Gaussian distribution.
Sanjoy Dasgupta, Daniel Hsu.
In Twentieth Annual Conference on Learning Theory. 2007.
[ local pdf file copy bib download bib ]
@inproceedings{dasgupta2007online,
  author = "Dasgupta, Sanjoy and Hsu, Daniel",
  booktitle = "Twentieth Annual Conference on Learning Theory",
  title = "On-line estimation with the multivariate Gaussian distribution",
  year = "2007"
}
A general agnostic active learning algorithm.
Sanjoy Dasgupta, Daniel Hsu, Claire Monteleoni.
In Advances in Neural Information Processing Systems 20. 2007.
[ local pdf file copy bib download bib ]
@inproceedings{dasgupta2007general,
  author = "Dasgupta, Sanjoy and Hsu, Daniel and Monteleoni, Claire",
  booktitle = "Advances in Neural Information Processing Systems 20",
  title = "A general agnostic active learning algorithm",
  year = "2007"
}
A concentration theorem for projections.
Sanjoy Dasgupta, Daniel Hsu, Nakul Verma.
In Twenty-Second Conference on Uncertainty in Artificial Intelligence. 2006.
[ local pdf file copy bib download bib ]
@inproceedings{dasgupta2006concentration,
  author = "Dasgupta, Sanjoy and Hsu, Daniel and Verma, Nakul",
  booktitle = "Twenty-Second Conference on Uncertainty in Artificial Intelligence",
  title = "A concentration theorem for projections",
  year = "2006"
}

Service

Associate Editor
ACM Transactions on Algorithms (TALG)
Senior PCs
Conference on Learning Theory (COLT) 2011, 2013, 2015, 2016, 2017
International Conference on Machine Learning (ICML) 2012, 2013, 2015, 2016, 2017
Conference on Neural Information Processing Systems (NIPS) 2012, 2013, 2017
International Conference on Artificial Intelligence and Statistics (AISTATS) 2016, 2017
Conference on Algorithmic Learning Theory (ALT) 2017
Program Committees
AAAI Conference on Artificial Intelligence (AAAI)
International Conference on Artificial Intelligence and Statistics (AISTATS)
International Conference on Machine Learning (ICML)
Conference on Neural Information Processing Systems (NIPS)
Conference on Uncertainty in Artificial Intelligence (UAI)
Workshop org
ICML 2014 Method of moments and spectral learning (June 25, 2014)
DIMACS/CCICADA Systems and analytics of big data (March 17–18, 2014)
NIPS 2013 Spectral learning (December 10, 2013)
ICML 2013 Spectral learning (June 21, 2013)
Seminar org
Foundations of Data Science Seminar (Fall 2015)
Local org
Conference on Learning Theory (COLT) 2016 (videos)

Teaching

Future courses
COMS 6998 Topics in Learning Theory (Fall 2017)
Past courses
COMS 4721 Machine Learning for Data Science (Spring 2016)
COMS 4771 Machine Learning (Spring 2015, Fall 2016)
COMS 4772 Advanced Machine Learning (Fall 2013, Fall 2014, Fall 2015, Fall 2016)
Tutorials
Simons Institute Foundations of Machine Learning Boot Camp (January 27, 2017)
AAAI 2014 Tensor decompositions for learning latent variable models (July 28, 2014)
ICML 2013 Tensor decomposition methods for latent variable model estimation (June 16, 2013)

&c

Funding
NSF DMREF: Deblurring our View of Atomic Arrangements in Complex Materials (website)
NSF IIS: Adaptive Information Extraction from Social Media ... (website)
Bloomberg Data Science Research Grant
Sloan Research Fellowship
Groups
Machine learning
Theory of computation
Foundations of data science