Daniel Hsu

Preprints

Two SVDs suffice: spectral decompositions for probabilistic topic models and latent Dirichlet allocation.
Animashree Anandkumar, Dean P. Foster, Daniel Hsu, Sham M. Kakade, and Yi-Kai Liu.
Preprint, 2012.
[arxiv]

A method of moments for mixture models and hidden Markov models.
Animashree Anandkumar, Daniel Hsu, and Sham M. Kakade.
Preprint, 2012.
[arxiv]

Learning high-dimensional mixtures of graphical models.
Animashree Anandkumar, Daniel Hsu, and Sham M. Kakade.
Preprint, 2012.
[arxiv]

A tail inequality for quadratic forms of subgaussian random vectors.
Daniel Hsu, Sham M. Kakade, and Tong Zhang.
Preprint, 2011.
[arxiv]

An analysis of random design linear regression.
Daniel Hsu, Sham M. Kakade, and Tong Zhang.
Preprint, 2011.
[pdf, arxiv]

Postprints

2012

Tail inequalities for sums of random matrices that depend on the intrinsic dimension.
Daniel Hsu, Sham M. Kakade, and Tong Zhang.
Electronic Communications in Probability, 17(14):1-13, 2012.
[pdf, link]

2011

Spectral methods for learning multivariate latent tree structure.
Animashree Anandkumar, Kamalika Chaudhuri, Daniel Hsu, Sham M. Kakade, Le Song, and Tong Zhang.
Advances in Neural Information Processing Systems 24, 2011.
[pdf, arxiv]

Stochastic convex optimization with bandit feedback.
Alekh Agarwal, Dean P. Foster, Daniel Hsu, Sham M. Kakade, and Alexander Rakhlin
Advances in Neural Information Processing Systems 24, 2011.
[pdf, arxiv]

Efficient optimal learning for contextual bandits.
Miroslav Dudik, Daniel Hsu, Satyen Kale, Nikos Karampatziakis, John Langford, Lev Reyzin, and Tong Zhang.
Twenty-Seventh Conference on Uncertainty in Artificial Intelligence, 2011.
[pdf]

Sample complexity bounds for differentially private learning.
Kamalika Chaudhuri and Daniel Hsu.
Twenty-Fourth Annual Conference on Learning Theory, 2011.
[pdf, talk slides]

Robust matrix decomposition with sparse corruptions.
Daniel Hsu, Sham M. Kakade, and Tong Zhang.
IEEE Transactions on Information Theory, 57(11):7221-7234, 2011.
[pdf, link]

2010

Agnostic active learning without constraints.
Alina Beygelzimer, Daniel Hsu, John Langford, and Tong Zhang.
Advances in Neural Information Processing Systems 23, 2010.
[pdf]

An online learning-based framework for tracking.
Kamalika Chaudhuri, Yoav Freund, and Daniel Hsu.
Twenty-Sixth Conference on Uncertainty in Artificial Intelligence, 2010.
[pdf]

Algorithms for active learning.
Daniel Hsu
Ph.D. dissertation, University of California, San Diego, 2010.
[pdf]

2009

Multi-label prediction via compressed sensing.
Daniel Hsu, Sham M. Kakade, John Langford, and Tong Zhang.
Advances in Neural Information Processing Systems 22, 2009.
[pdf, talk slides]

A parameter-free hedging algorithm.
Kamalika Chaudhuri, Yoav Freund, and Daniel Hsu.
Advances in Neural Information Processing Systems 22, 2009.
[pdf]

A spectral algorithm for learning hidden Markov models.
Daniel Hsu, Sham M. Kakade, and Tong Zhang.
Twenty-Second Annual Conference on Learning Theory, 2009.
Journal of Computer and System Sciences (accepted, but it's Elsevier...).
[pdf, talk slides]

2008 and earlier

Hierarchical sampling for active learning.
Sanjoy Dasgupta and Daniel Hsu.
Twenty-Fifth International Conference on Machine Learning, 2008.
[pdf]

A general agnostic active learning algorithm.
Sanjoy Dasgupta, Daniel Hsu, and Claire Monteleoni.
Advances in Neural Information Processing Systems 20, 2007.
[pdf]

On-line estimation with the multivariate Gaussian distribution.
Sanjoy Dasgupta and Daniel Hsu.
Twentieth Annual Conference on Learning Theory, 2007.
[pdf]

A concentration theorem for projections.
Sanjoy Dasgupta, Daniel Hsu, and Nakul Verma.
Twenty-Second Conference on Uncertainty in Artificial Intelligence, 2006.
[pdf]