# Sham M. Kakade

According to our database

Collaborative distances:

^{1}, Sham M. Kakade authored at least 102 papers between 1999 and 2018.Collaborative distances:

## Timeline

#### Legend:

Book In proceedings Article PhD thesis Other## Links

#### Homepage:

#### On csauthors.net:

## Bibliography

2018

Prediction with a short memory.

Proceedings of the 50th Annual ACM SIGACT Symposium on Theory of Computing, 2018

A Smoother Way to Train Structured Prediction Models.

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Provably Correct Automatic Sub-Differentiation for Qualified Programs.

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

On the Insufficiency of Existing Momentum Schemes for Stochastic Optimization.

Proceedings of the 2018 Information Theory and Applications Workshop, 2018

Recovering Structured Probability Matrices.

Proceedings of the 9th Innovations in Theoretical Computer Science Conference, 2018

Global Convergence of Policy Gradient Methods for the Linear Quadratic Regulator.

Proceedings of the 35th International Conference on Machine Learning, 2018

Invariances and Data Augmentation for Supervised Music Transcription.

Proceedings of the 2018 IEEE International Conference on Acoustics, 2018

Accelerating Stochastic Gradient Descent for Least Squares Regression.

Proceedings of the Conference On Learning Theory, 2018

2017

Parallelizing Stochastic Gradient Descent for Least Squares Regression: Mini-batching, Averaging, and Model Misspecification.

Journal of Machine Learning Research, 2017

Learning Overcomplete HMMs.

Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

Towards Generalization and Simplicity in Continuous Control.

Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

How to Escape Saddle Points Efficiently.

Proceedings of the 34th International Conference on Machine Learning, 2017

A Markov Chain Theory Approach to Characterizing the Minimax Optimality of Stochastic Gradient Descent (for Least Squares).

Proceedings of the 37th IARCS Annual Conference on Foundations of Software Technology and Theoretical Computer Science, 2017

Global Convergence of Non-Convex Gradient Descent for Computing Matrix Squareroot.

Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, 2017

2016

Minimal Realization Problems for Hidden Markov Models.

IEEE Trans. Signal Processing, 2016

Provable Efficient Online Matrix Completion via Non-convex Stochastic Gradient Descent.

Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016

Efficient Algorithms for Large-scale Generalized Eigenvector Computation and Canonical Correlation Analysis.

Proceedings of the 33nd International Conference on Machine Learning, 2016

Faster Eigenvector Computation via Shift-and-Invert Preconditioning.

Proceedings of the 33nd International Conference on Machine Learning, 2016

Streaming PCA: Matching Matrix Bernstein and Near-Optimal Finite Sample Guarantees for Oja's Algorithm.

Proceedings of the 29th Conference on Learning Theory, 2016

2015

Learning Mixtures of Gaussians in High Dimensions.

Proceedings of the Forty-Seventh Annual ACM on Symposium on Theory of Computing, 2015

Super-Resolution Off the Grid.

Proceedings of the Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, 2015

Convergence Rates of Active Learning for Maximum Likelihood Estimation.

Proceedings of the Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, 2015

Un-regularizing: approximate proximal point and faster stochastic algorithms for empirical risk minimization.

Proceedings of the 32nd International Conference on Machine Learning, 2015

A Linear Dynamical System Model for Text.

Proceedings of the 32nd International Conference on Machine Learning, 2015

Competing with the Empirical Risk Minimizer in a Single Pass.

Proceedings of The 28th Conference on Learning Theory, 2015

Tensor Decompositions for Learning Latent Variable Models (A Survey for ALT).

Proceedings of the Algorithmic Learning Theory - 26th International Conference, 2015

2014

Tensor decompositions for learning latent variable models.

Journal of Machine Learning Research, 2014

A tensor approach to learning mixed membership community models.

Journal of Machine Learning Research, 2014

Least Squares Revisited: Scalable Approaches for Multi-class Prediction.

Proceedings of the 31th International Conference on Machine Learning, 2014

Minimal realization problem for Hidden Markov Models.

Proceedings of the 52nd Annual Allerton Conference on Communication, 2014

2013

A risk comparison of ordinary least squares vs ridge regression.

Journal of Machine Learning Research, 2013

Optimal Dynamic Mechanism Design and the Virtual-Pivot Mechanism.

Operations Research, 2013

When are Overcomplete Topic Models Identifiable? Uniqueness of Tensor Tucker Decompositions with Structured Sparsity.

Proceedings of the Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013. Proceedings of a meeting held December 5-8, 2013

Learning mixtures of spherical gaussians: moment methods and spectral decompositions.

Proceedings of the Innovations in Theoretical Computer Science, 2013

Learning Linear Bayesian Networks with Latent Variables.

Proceedings of the 30th International Conference on Machine Learning, 2013

A Tensor Spectral Approach to Learning Mixed Membership Community Models.

Proceedings of the COLT 2013, 2013

2012

Information-Theoretic Regret Bounds for Gaussian Process Optimization in the Bandit Setting.

IEEE Trans. Information Theory, 2012

Domain Adaptation: A Small Sample Statistical Approach.

Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics, 2012

Regularization Techniques for Learning with Matrices.

Journal of Machine Learning Research, 2012

Random Design Analysis of Ridge Regression.

Proceedings of the COLT 2012, 2012

(weak) Calibration is Computationally Hard.

Proceedings of the COLT 2012, 2012

Towards Minimax Policies for Online Linear Optimization with Bandit Feedback.

Proceedings of the COLT 2012, 2012

A Method of Moments for Mixture Models and Hidden Markov Models.

Proceedings of the COLT 2012, 2012

Identifiability and Unmixing of Latent Parse Trees.

Proceedings of the Advances in Neural Information Processing Systems 25: 26th Annual Conference on Neural Information Processing Systems 2012. Proceedings of a meeting held December 3-6, 2012

Learning Mixtures of Tree Graphical Models.

Proceedings of the Advances in Neural Information Processing Systems 25: 26th Annual Conference on Neural Information Processing Systems 2012. Proceedings of a meeting held December 3-6, 2012

A Spectral Algorithm for Latent Dirichlet Allocation.

Proceedings of the Advances in Neural Information Processing Systems 25: 26th Annual Conference on Neural Information Processing Systems 2012. Proceedings of a meeting held December 3-6, 2012

2011

Robust Matrix Decomposition With Sparse Corruptions.

IEEE Trans. Information Theory, 2011

Optimal dynamic mechanism design via a virtual VCG mechanism.

SIGecom Exchanges, 2011

Preface.

Proceedings of the COLT 2011, 2011

Domain Adaptation with Coupled Subspaces.

Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, 2011

Efficient Learning of Generalized Linear and Single Index Models with Isotonic Regression.

Proceedings of the Advances in Neural Information Processing Systems 24: 25th Annual Conference on Neural Information Processing Systems 2011. Proceedings of a meeting held 12-14 December 2011, 2011

Spectral Methods for Learning Multivariate Latent Tree Structure.

Proceedings of the Advances in Neural Information Processing Systems 24: 25th Annual Conference on Neural Information Processing Systems 2011. Proceedings of a meeting held 12-14 December 2011, 2011

Stochastic convex optimization with bandit feedback.

Proceedings of the Advances in Neural Information Processing Systems 24: 25th Annual Conference on Neural Information Processing Systems 2011. Proceedings of a meeting held 12-14 December 2011, 2011

2010

Guest editorial: special issue on learning theory.

Machine Learning, 2010

Learning Exponential Families in High-Dimensions: Strong Convexity and Sparsity.

Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, 2010

Learning from Logged Implicit Exploration Data.

Proceedings of the Advances in Neural Information Processing Systems 23: 24th Annual Conference on Neural Information Processing Systems 2010. Proceedings of a meeting held 6-9 December 2010, 2010

Gaussian Process Optimization in the Bandit Setting: No Regret and Experimental Design.

Proceedings of the 27th International Conference on Machine Learning (ICML-10), 2010

2009

Online Markov Decision Processes.

Math. Oper. Res., 2009

The price of truthfulness for pay-per-click auctions.

Proceedings of the Proceedings 10th ACM Conference on Electronic Commerce (EC-2009), 2009

Multi-Label Prediction via Compressed Sensing.

Proceedings of the Advances in Neural Information Processing Systems 22: 23rd Annual Conference on Neural Information Processing Systems 2009. Proceedings of a meeting held 7-10 December 2009, 2009

Multi-view clustering via canonical correlation analysis.

Proceedings of the 26th Annual International Conference on Machine Learning, 2009

A Spectral Algorithm for Learning Hidden Markov Models.

Proceedings of the COLT 2009, 2009

2008

Information Consistency of Nonparametric Gaussian Process Methods.

IEEE Trans. Information Theory, 2008

Mind the Duality Gap: Logarithmic regret algorithms for online optimization.

Proceedings of the Advances in Neural Information Processing Systems 21, 2008

On the Generalization Ability of Online Strongly Convex Programming Algorithms.

Proceedings of the Advances in Neural Information Processing Systems 21, 2008

On the Complexity of Linear Prediction: Risk Bounds, Margin Bounds, and Regularization.

Proceedings of the Advances in Neural Information Processing Systems 21, 2008

Efficient bandit algorithms for online multiclass prediction.

Proceedings of the Machine Learning, 2008

An Information Theoretic Framework for Multi-view Learning.

Proceedings of the 21st Annual Conference on Learning Theory, 2008

Stochastic Linear Optimization under Bandit Feedback.

Proceedings of the 21st Annual Conference on Learning Theory, 2008

High-Probability Regret Bounds for Bandit Online Linear Optimization.

Proceedings of the 21st Annual Conference on Learning Theory, 2008

2007

Maximum Entropy Correlated Equilibria.

Proceedings of the Eleventh International Conference on Artificial Intelligence and Statistics, 2007

Playing games with approximation algorithms.

Proceedings of the 39th Annual ACM Symposium on Theory of Computing, 2007

The Price of Bandit Information for Online Optimization.

Proceedings of the Advances in Neural Information Processing Systems 20, 2007

The Value of Observation for Monitoring Dynamic Systems.

Proceedings of the IJCAI 2007, 2007

Leveragingarchivalvideo for building face datasets.

Proceedings of the IEEE 11th International Conference on Computer Vision, 2007

Multi-view Regression Via Canonical Correlation Analysis.

Proceedings of the Learning Theory, 20th Annual Conference on Learning Theory, 2007

2006

(In)Stability properties of limit order dynamics.

Proceedings of the Proceedings 7th ACM Conference on Electronic Commerce (EC-2006), 2006

Cover trees for nearest neighbor.

Proceedings of the Machine Learning, 2006

2005

Planning in POMDPs Using Multiplicity Automata.

Proceedings of the UAI '05, 2005

Worst-Case Bounds for Gaussian Process Models.

Proceedings of the Advances in Neural Information Processing Systems 18 [Neural Information Processing Systems, 2005

From Batch to Transductive Online Learning.

Proceedings of the Advances in Neural Information Processing Systems 18 [Neural Information Processing Systems, 2005

Reinforcement Learning in POMDPs Without Resets.

Proceedings of the IJCAI-05, Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence, Edinburgh, Scotland, UK, July 30, 2005

Trading in Markovian Price Models.

Proceedings of the Learning Theory, 18th Annual Conference on Learning Theory, 2005

2004

Competitive algorithms for VWAP and limit order trading.

Proceedings of the Proceedings 5th ACM Conference on Electronic Commerce (EC-2004), 2004

Online Bounds for Bayesian Algorithms.

Proceedings of the Advances in Neural Information Processing Systems 17 [Neural Information Processing Systems, 2004

Economic Properties of Social Networks.

Proceedings of the Advances in Neural Information Processing Systems 17 [Neural Information Processing Systems, 2004

Experts in a Markov Decision Process.

Proceedings of the Advances in Neural Information Processing Systems 17 [Neural Information Processing Systems, 2004

Graphical Economics.

Proceedings of the Learning Theory, 17th Annual Conference on Learning Theory, 2004

Deterministic Calibration and Nash Equilibrium.

Proceedings of the Learning Theory, 17th Annual Conference on Learning Theory, 2004

2003

Correlated equilibria in graphical games.

Proceedings of the Proceedings 4th ACM Conference on Electronic Commerce (EC-2003), 2003

Policy Search by Dynamic Programming.

Proceedings of the Advances in Neural Information Processing Systems 16 [Neural Information Processing Systems, 2003

Exploration in Metric State Spaces.

Proceedings of the Machine Learning, 2003

2002

Dopamine: generalization and bonuses.

Neural Networks, 2002

Opponent interactions between serotonin and dopamine.

Neural Networks, 2002

Competitive Analysis of the Explore/Exploit Tradeoff.

Proceedings of the Machine Learning, 2002

An Alternate Objective Function for Markovian Fields.

Proceedings of the Machine Learning, 2002

Approximately Optimal Approximate Reinforcement Learning.

Proceedings of the Machine Learning, 2002

2001

A Natural Policy Gradient.

Proceedings of the Advances in Neural Information Processing Systems 14 [Neural Information Processing Systems: Natural and Synthetic, 2001

Optimizing Average Reward Using Discounted Rewards.

Proceedings of the Computational Learning Theory, 2001

2000

Dopamine Bonuses.

Proceedings of the Advances in Neural Information Processing Systems 13, 2000

Explaining Away in Weight Space.

Proceedings of the Advances in Neural Information Processing Systems 13, 2000

1999

Acquisition in Autoshaping.

Proceedings of the Advances in Neural Information Processing Systems 12, [NIPS Conference, Denver, Colorado, USA, November 29, 1999