Sham M. Kakade

发表

Variance Reduction Methods for Sublinear Reinforcement Learning pdf

Sham M. Kakade, Mengdi Wang, Lin F. Yang, 2018, ArXiv.

Online Bounds for Bayesian Algorithms

Sham M. Kakade, Andrew Y. Ng, A. Ng, 2004, NIPS.

Provably Efficient Maximum Entropy Exploration pdf

Sham M. Kakade, Karan Singh, Elad Hazan, 2018, ICML.

Global Convergence of Policy Gradient Methods for Linearized Control Problems pdf

Sham M. Kakade, Mehran Mesbahi, Maryam Fazel, 2018, ICML 2018.

Faster Eigenvector Computation via Shift-and-Invert Preconditioning

Sham M. Kakade, Praneeth Netrapalli, Elad Hazan, 2016, ICML.

Variance Reduction for Policy Gradient with Action-Dependent Factorized Baselines pdf

Alexandre M. Bayen, Pieter Abbeel, Sham M. Kakade, 2018, ICLR.

Global Convergence of Policy Gradient Methods for the Linear Quadratic Regulator

Sham M. Kakade, Mehran Mesbahi, Maryam Fazel, 2018, ICML.

An Optimal Dynamic Mechanism for Multi-Armed Bandit Processes pdf

Sham M. Kakade, Ilan Lobel, Hamid Nazerzadeh, 2010, ArXiv.

(weak) Calibration is Computationally Hard pdf

Sham M. Kakade, Elad Hazan, S. Kakade, 2012, COLT.

The Nonstochastic Control Problem

Sham M. Kakade, Karan Singh, Elad Hazan, 2020, ALT.

A Method of Moments for Mixture Models and Hidden Markov Models

Anima Anandkumar, Sham M. Kakade, Daniel J. Hsu, 2012, COLT.

On the Insufficiency of Existing Momentum Schemes for Stochastic Optimization

Prateek Jain, Sham M. Kakade, Praneeth Netrapalli, 2018, 2018 Information Theory and Applications Workshop (ITA).

Competitive Analysis of the Explore/Exploit Tradeoff

John Langford, Sham M. Kakade, Martin Zinkevich, 2002, ICML.

Robust Aggregation for Federated Learning pdf

Zaïd Harchaoui, Sham M. Kakade, Venkata Krishna Pillutla, 2019, IEEE Transactions on Signal Processing.

Trading in Markovian Price Models

Sham M. Kakade, Michael Kearns, S. Kakade, 2005, COLT.

When are overcomplete topic models identifiable? uniqueness of tensor tucker decompositions with structured sparsity

Anima Anandkumar, Sham M. Kakade, Majid Janzamin, 2013, J. Mach. Learn. Res..

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

Anima Anandkumar, Matus Telgarsky, Sham M. Kakade, 2015, ALT.

A tensor approach to learning mixed membership community models

Anima Anandkumar, Sham M. Kakade, Rong Ge, 2013, J. Mach. Learn. Res..

An Information Theoretic Framework for Multi-view Learning

Sham M. Kakade, Karthik Sridharan, S. Kakade, 2008, COLT.

Calibration, Entropy Rates, and Memory in Language Models

Sham M. Kakade, Yi Zhang, Mark Braverman, 2019, ICML.

Opponent interactions between serotonin and dopamine

Sham M. Kakade, Nathaniel D. Daw, Peter Dayan, 2002, Neural Networks.

Policy Search by Dynamic Programming

Jeff G. Schneider, Sham M. Kakade, Andrew Y. Ng, 2003, NIPS.

Accelerating Stochastic Gradient Descent pdf

Prateek Jain, Sham M. Kakade, Praneeth Netrapalli, 2017, ArXiv.

Towards Generalization and Simplicity in Continuous Control

Sham M. Kakade, Emanuel Todorov, Aravind Rajeswaran, 2017, NIPS.

What are the Statistical Limits of Offline RL with Linear Function Approximation? pdf

Ruosong Wang, Sham M. Kakade, Dean P. Foster, 2020, ICLR.

Deterministic calibration and Nash equilibrium

Sham M. Kakade, Dean P. Foster, S. Kakade, 2004, Journal of computer and system sciences (Print).

Optimizing Average Reward Using Discounted Rewards

Sham M. Kakade, S. Kakade, 2001, COLT/EuroCOLT.

Accelerating Stochastic Gradient Descent

Prateek Jain, Sham M. Kakade, Praneeth Netrapalli, 2017, COLT.

On the Theory of Policy Gradient Methods: Optimality, Approximation, and Distribution Shift

Sham M. Kakade, Jason D. Lee, Gaurav Mahajan, 2019, J. Mach. Learn. Res..

An Alternate Objective Function for Markovian Fields

Yee Whye Teh, Sham M. Kakade, Sam T. Roweis, 2002, ICML.

Stochastic Linear Optimization under Bandit Feedback

Thomas P. Hayes, Sham M. Kakade, Varsha Dani, 2008, COLT.

The Illusion of Change: Correcting for Bias when Inferring Changes in Sparse, Societal-Scale Data

Sham M. Kakade, Joshua Blumenstock, Ramya Korlakai Vinayak, 2019, WWW 2019.

Learning from Logged Implicit Exploration Data

Lihong Li, Sham M. Kakade, John Langford, 2010, NIPS.

A Natural Policy Gradient

Sham M. Kakade, S. Kakade, 2001, NIPS.

A Short Note on Concentration Inequalities for Random Vectors with SubGaussian Norm pdf

Michael I. Jordan, Sham M. Kakade, Praneeth Netrapalli, 2019, ArXiv.

Playing Games with Approximation Algorithms

Adam Tauman Kalai, Sham M. Kakade, Katrina Ligett, 2009, SIAM J. Comput..

Competing with the Empirical Risk Minimizer in a Single Pass pdf

Sham M. Kakade, Aaron Sidford, Rong Ge, 2014, COLT.

Playing games with approximation algorithms

Adam Tauman Kalai, Sham M. Kakade, Katrina Ligett, 2007, STOC '07.

Invariances and Data Augmentation for Supervised Music Transcription

Zaïd Harchaoui, Sham M. Kakade, Dean P. Foster, 2017, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

On the sample complexity of reinforcement learning.

Sham M. Kakade, S. Kakade, 2003 .

Optimal dynamic mechanism design via a virtual VCG mechanism

Sham M. Kakade, Ilan Lobel, Hamid Nazerzadeh, 2011, SECO.

An Analysis of Random Design Linear Regression pdf

Sham M. Kakade, Tong Zhang, Daniel J. Hsu, 2011, ArXiv.

Cover trees for nearest neighbor

John Langford, Sham M. Kakade, Alina Beygelzimer, 2006, ICML.

A Smoother Way to Train Structured Prediction Models

Zaïd Harchaoui, Sham M. Kakade, Venkata Krishna Pillutla, 2019, NeurIPS.

The Value of Observation for Monitoring Dynamic Systems

Yishay Mansour, Sham M. Kakade, Eyal Even-Dar, 2007, IJCAI.

Online Markov Decision Processes

Yishay Mansour, Sham M. Kakade, Eyal Even-Dar, 2009, Math. Oper. Res..

Robust Matrix Decomposition with Outliers pdf

Sham M. Kakade, Tong Zhang, Daniel J. Hsu, 2010, ArXiv.

Robust Matrix Decomposition With Sparse Corruptions

Sham M. Kakade, Tong Zhang, Daniel J. Hsu, 2011, IEEE Transactions on Information Theory.

High-Probability Regret Bounds for Bandit Online Linear Optimization

Thomas P. Hayes, Ambuj Tewari, Peter L. Bartlett, 2008, COLT.

Efficient bandit algorithms for online multiclass prediction

Ambuj Tewari, Sham M. Kakade, Shai Shalev-Shwartz, 2008, ICML '08.

Spectral Methods for Learning Multivariate Latent Tree Structure

Le Song, Anima Anandkumar, Sham M. Kakade, 2011, NIPS.

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

Ambuj Tewari, Sham M. Kakade, Karthik Sridharan, 2008, NIPS.

Gaussian Process Bandits without Regret: An Experimental Design Approach pdf

Andreas Krause, Sham M. Kakade, Matthias W. Seeger, 2009, ArXiv.

Applications of strong convexity--strong smoothness duality to learning with matrices pdf

Ambuj Tewari, Sham M. Kakade, Shai Shalev-Shwartz, 2009, ArXiv.

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

Prateek Jain, Sham M. Kakade, Venkata Krishna Pillutla, 2017, FSTTCS.

John Langford, Luis E. Ortiz, Sham M. Kakade, 2003, EC '03.

Guest editorial: special issue on learning theory

Sham M. Kakade, Ping Li, 2010, Machine Learning.

Analysis of a randomized approximation scheme for matrix multiplication pdf

Sham M. Kakade, Tong Zhang, Daniel J. Hsu, 2012, ArXiv.

The Step Decay Schedule: A Near Optimal, Geometrically Decaying Learning Rate Procedure

Sham M. Kakade, Praneeth Netrapalli, Rong Ge, 2019, NeurIPS.

Multi-view clustering via canonical correlation analysis

Sham M. Kakade, Kamalika Chaudhuri, Karthik Sridharan, 2009, ICML '09.

Optimality and Approximation with Policy Gradient Methods in Markov Decision Processes

Sham M. Kakade, Jason D. Lee, Gaurav Mahajan, 2019, COLT.

Learning Mixtures of Tree Graphical Models

Anima Anandkumar, Sham M. Kakade, Furong Huang, 2012, NIPS.

Provably Correct Automatic Subdifferentiation for Qualified Programs

Sham M. Kakade, Jason D. Lee, S. Kakade, 2018, NeurIPS.

Few-Shot Learning via Learning the Representation, Provably pdf

Sham M. Kakade, Wei Hu, Jason D. Lee, 2020, ICLR.

Information Consistency of Nonparametric Gaussian Process Methods

Sham M. Kakade, Dean P. Foster, Matthias W. Seeger, 2008, IEEE Transactions on Information Theory.

Optimal Dynamic Mechanism Design and the Virtual Pivot Mechanism

Sham M. Kakade, Ilan Lobel, Hamid Nazerzadeh, 2013, Oper. Res..

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

Andreas Krause, Sham M. Kakade, Matthias W. Seeger, 2009, IEEE Transactions on Information Theory.

Acquisition in Autoshaping

Peter Dayan, Sham M. Kakade, S. Kakade, 1999, NIPS.

Domain Adaptation: A Small Sample Statistical Approach

Ruslan Salakhutdinov, Sham M. Kakade, Dean P. Foster, 2012, AISTATS.

Learning Overcomplete HMMs

Vatsal Sharan, Sham M. Kakade, Gregory Valiant, 2017, NIPS.

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

Prateek Jain, Sham M. Kakade, Praneeth Netrapalli, 2015, AISTATS.

37th IARCS Annual Conference on Foundations of Software Technology and Theoretical Computer Science, FSTTCS 2017, December 11-15, 2017, Kanpur, India

Prateek Jain, Sham M. Kakade, Venkata Krishna Pillutla, 2018, FSTTCS.

Learning Features of Music from Scratch pdf

Zaïd Harchaoui, Sham M. Kakade, John Thickstun, 2016, ICLR.

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

Sham M. Kakade, Aaron Sidford, Rong Ge, 2015, ICML.

Exploration in Metric State Spaces

John Langford, Sham M. Kakade, Michael Kearns, 2003, ICML.

Computing Matrix Squareroot via Non Convex Local Search pdf

Prateek Jain, Sham M. Kakade, Praneeth Netrapalli, 2015, ArXiv.

(In)Stability properties of limit order dynamics

Yishay Mansour, Sham M. Kakade, Michael Kearns, 2006, EC '06.

Convergence Rates of Active Learning for Maximum Likelihood Estimation

Sham M. Kakade, Kamalika Chaudhuri, Sujay Sanghavi, 2015, NIPS.

The Illusion of Change: Correcting for Biases in Change Inference for Sparse, Societal-Scale Data

Jacob Shapiro, Sham M. Kakade, Ramya Korlakai Vinayak, 2019, WWW.

Multi-view Regression Via Canonical Correlation Analysis

Sham M. Kakade, Dean P. Foster, S. Kakade, 2007, COLT.

Minimal realization problem for Hidden Markov Models

Munther A. Dahleh, Qingqing Huang, Sham M. Kakade, 2014, 2014 52nd Annual Allerton Conference on Communication, Control, and Computing (Allerton).

Maximum Entropy Correlated Equilibria

Luis E. Ortiz, Sham M. Kakade, Robert E. Schapire, 2007, AISTATS.

Sample-Efficient Reinforcement Learning of Undercomplete POMDPs pdf

Akshay Krishnamurthy, Qinghua Liu, Sham M. Kakade, 2020, NeurIPS.

Explaining Away in Weight Space

Peter Dayan, Sham M. Kakade, S. Kakade, 2000, NIPS.

Plan Online, Learn Offline: Efficient Learning and Exploration via Model-Based Control pdf

Sham M. Kakade, Emanuel Todorov, Aravind Rajeswaran, 2018, ICLR.

Approximately Optimal Approximate Reinforcement Learning

John Langford, Sham M. Kakade, S. Kakade, 2002, ICML.

Online Control with Adversarial Disturbances

Sham M. Kakade, Karan Singh, Naman Agarwal, 2019, ICML.

Deterministic calibration and Nash equilibrium

Sham M. Kakade, Dean P. Foster, S. Kakade, 2004, J. Comput. Syst. Sci..

On the Generalization Ability of Online Strongly Convex Programming Algorithms

Ambuj Tewari, Sham M. Kakade, S. Kakade, 2008, NIPS.

Canonical Correlation Analysis for Analyzing Sequences of Medical Billing Codes pdf

Corinne L. Jones, Sham M. Kakade, Abraham D. Flaxman, 2016, ArXiv.

Matching Matrix Bernstein with Little Memory: Near-Optimal Finite Sample Guarantees for Oja's Algorithm pdf

Prateek Jain, Sham M. Kakade, Praneeth Netrapalli, 2016, ArXiv.

Prediction with a short memory

Vatsal Sharan, Sham M. Kakade, Percy Liang, 2016, STOC.

Meta-Learning

Sergey Levine, Sham M. Kakade, Chelsea Finn, 2019, Automated Machine Learning.

Calibration via Regression

Sham M. Kakade, Dean P. Foster, S. Kakade, 2006, 2006 IEEE Information Theory Workshop - ITW '06 Punta del Este.

Learning mixtures of spherical gaussians: moment methods and spectral decompositions

Sham M. Kakade, Daniel J. Hsu, S. Kakade, 2012, ITCS '13.

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

Prateek Jain, Sham M. Kakade, Praneeth Netrapalli, 2016, J. Mach. Learn. Res..

A risk comparison of ordinary least squares vs ridge regression

Sham M. Kakade, Dean P. Foster, Lyle H. Ungar, 2011, J. Mach. Learn. Res..

Rethinking learning rate schedules for stochastic optimization

Rong Ge, Sham M. Kakade, Praneeth Netrapalli, 2018 .

Towards Minimax Policies for Online Linear Optimization with Bandit Feedback pdf

Sham M. Kakade, Sébastien Bubeck, Nicolò Cesa-Bianchi, 2012, COLT.

The price of truthfulness for pay-per-click auctions

Nikhil R. Devanur, Sham M. Kakade, S. Kakade, 2009, EC '09.

Learning Mixtures of Gaussians in High Dimensions

Qingqing Huang, Sham M. Kakade, Rong Ge, 2015, STOC.

Is a Good Representation Sufficient for Sample Efficient Reinforcement Learning? pdf

Ruosong Wang, Sham M. Kakade, Lin F. Yang, 2020, ICLR.

Stochastic Subgradient Method Converges on Tame Functions

Dmitriy Drusvyatskiy, Sham M. Kakade, Jason D. Lee, 2018, Foundations of Computational Mathematics.

Is Long Horizon Reinforcement Learning More Difficult Than Short Horizon Reinforcement Learning? pdf

Ruosong Wang, Sham M. Kakade, Lin F. Yang, 2020, ArXiv.

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

Sham M. Kakade, Praneeth Netrapalli, Chi Jin, 2016, NIPS.

Domain Adaptation: Overfitting and Small Sample Statistics pdf

Ruslan Salakhutdinov, Sham M. Kakade, Dean P. Foster, 2011, ArXiv.

Parallelizing Stochastic Approximation Through Mini-Batching and Tail-Averaging pdf

Prateek Jain, Sham M. Kakade, Praneeth Netrapalli, 2016, ArXiv.

Two SVDs Suffice: Spectral decompositions for probabilistic topic modeling and latent Dirichlet allocation pdf

Anima Anandkumar, Sham M. Kakade, Dean P. Foster, 2012, NIPS 2012.

A tail inequality for quadratic forms of subgaussian random vectors pdf

Sham M. Kakade, Tong Zhang, Daniel J. Hsu, 2011, ArXiv.

Optimal Estimation of Change in a Population of Parameters pdf

Sham M. Kakade, Weihao Kong, Ramya Korlakai Vinayak, 2019, ArXiv.

PACT: Privacy-Sensitive Protocols And Mechanisms for Mobile Contact Tracing pdf

Eric Horvitz, Stefano Tessaro, Tadayoshi Kohno, 2020, IEEE Data Eng. Bull..

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

Prateek Jain, Sham M. Kakade, Praneeth Netrapalli, 2016, COLT.

Leveraging archival video for building face datasets

Sham M. Kakade, Deva Ramanan, Simon Baker, 2007, 2007 IEEE 11th International Conference on Computer Vision.

Leverage Score Sampling for Faster Accelerated Regression and ERM

Yin Tat Lee, Sham M. Kakade, Praneeth Netrapalli, 2017, ALT.

Learning Linear Bayesian Networks with Latent Variables

Adel Javanmard, Anima Anandkumar, Sham M. Kakade, 2012, ICML.

Learning High-Dimensional Mixtures of Graphical Models pdf

Anima Anandkumar, Sham M. Kakade, Daniel J. Hsu, 2012, ArXiv.

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

Adam Tauman Kalai, Varun Kanade, Ohad Shamir, 2011, NIPS.

The Price of Bandit Information for Online Optimization

Thomas P. Hayes, Sham M. Kakade, Varsha Dani, 2007, NIPS.

Domain Adaptation with Coupled Subspaces

John Blitzer, Sham M. Kakade, Dean P. Foster, 2011, AISTATS.

Game Theoretical Algorithms for Intelligent Networking

Luis E. Ortiz, Sham M. Kakade, Michael Kerns, 2005 .

Minimal Realization Problems for Hidden Markov Models

Munther A. Dahleh, Qingqing Huang, Sham M. Kakade, 2014, IEEE Transactions on Signal Processing.

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

Sham M. Kakade, Praneeth Netrapalli, Aaron Sidford, 2016, ICML.

Competitive algorithms for VWAP and limit order trading

Yishay Mansour, Luis E. Ortiz, Sham M. Kakade, 2004, EC '04.

From Batch to Transductive Online Learning

Adam Tauman Kalai, Sham M. Kakade, S. Kakade, 2005, NIPS.

Tensor decompositions for learning latent variable models pdf

Anima Anandkumar, Matus Telgarsky, Sham M. Kakade, 2012, J. Mach. Learn. Res..

Mind the Duality Gap: Logarithmic regret algorithms for online optimization

Sham M. Kakade, Shai Shalev-Shwartz, S. Kakade, 2008, NIPS.

Super-Resolution Off the Grid

Qingqing Huang, Sham M. Kakade, S. Kakade, 2015, NIPS.

A Linear Dynamical System Model for Text

Sham M. Kakade, David Belanger, S. Kakade, 2015, ICML.

Open Problem: Do Good Algorithms Necessarily Query Bad Points?

Prateek Jain, Sham M. Kakade, Praneeth Netrapalli, 2019, COLT.

Worst-Case Bounds for Gaussian Process Models

Sham M. Kakade, Dean P. Foster, Matthias W. Seeger, 2005, NIPS.

Model-Based Multi-Agent RL in Zero-Sum Markov Games with Near-Optimal Sample Complexity pdf

Sham M. Kakade, Lin F. Yang, Kaiqing Zhang, 2020, NeurIPS.

Is Long Horizon RL More Difficult Than Short Horizon RL?

Ruosong Wang, Sham M. Kakade, Lin F. Yang, 2020, NeurIPS.

Graphical Economics

Luis E. Ortiz, Sham M. Kakade, Michael Kearns, 2004, COLT.

A Spectral Algorithm for Latent Dirichlet Allocation

Anima Anandkumar, Sham M. Kakade, Dean P. Foster, 2012, Algorithmica.

A Tensor Spectral Approach to Learning Mixed Membership Community Models pdf

Anima Anandkumar, Sham M. Kakade, Rong Ge, 2013, COLT.

Maximum Likelihood Estimation for Learning Populations of Parameters

Sham M. Kakade, Gregory Valiant, Weihao Kong, 2019, ICML.

Recovering Structured Probability Matrices

Qingqing Huang, Sham M. Kakade, Gregory Valiant, 2018, ITCS.

Dopamine: generalization and bonuses

Peter Dayan, Sham M. Kakade, S. Kakade, 2002, Neural Networks.

Economic Properties of Social Networks

Luis E. Ortiz, Sham M. Kakade, Robin Pemantle, 2004, NIPS.

Experts in a Markov Decision Process

Yishay Mansour, Sham M. Kakade, Eyal Even-Dar, 2004, NIPS.

On Nonconvex Optimization for Machine Learning: Gradients, Stochasticity, and Saddle Points

Michael I. Jordan, Sham M. Kakade, Praneeth Netrapalli, 2019 .

Least Squares Revisited: Scalable Approaches for Multi-class Prediction

Le Song, Nikos Karampatziakis, Sham M. Kakade, 2013, ICML.

Learning Topic Models and Latent Bayesian Networks Under Expansion Constraints

Adel Javanmard, Sham M. Kakade, Daniel J. Hsu, 2012, 1209.5350.

Robust Shift-and-Invert Preconditioning: Faster and More Sample Efficient Algorithms for Eigenvector Computation pdf

Sham M. Kakade, Praneeth Netrapalli, Aaron Sidford, 2015, ArXiv.

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

Ambuj Tewari, Ohad Shamir, Sham M. Kakade, 2009, AISTATS.

Multi-Label Prediction via Compressed Sensing

John Langford, Sham M. Kakade, Tong Zhang, 2009, NIPS.

Stochastic Convex Optimization with Bandit Feedback

Sham M. Kakade, Dean P. Foster, Alekh Agarwal, 2011, SIAM J. Optim..

Identifiability and Unmixing of Latent Parse Trees

Sham M. Kakade, Percy Liang, Daniel J. Hsu, 2012, NIPS.

Regularization Techniques for Learning with Matrices

Ambuj Tewari, Sham M. Kakade, Shai Shalev-Shwartz, 2009, J. Mach. Learn. Res..

Stochastic Gradient Descent Escapes Saddle Points Efficiently pdf

Michael I. Jordan, Sham M. Kakade, Praneeth Netrapalli, 2019, ArXiv.

Learning Gaussian Mixture Models: Moment Methods and Spectral Decompositions pdf

Sham M. Kakade, Daniel J. Hsu, S. Kakade, 2012, arXiv.org.

Dimension-free tail inequalities for sums of random matrices pdf

Sham M. Kakade, Tong Zhang, Daniel J. Hsu, 2011, ArXiv.

Dopamine Bonuses

Peter Dayan, Sham M. Kakade, S. Kakade, 2000, NIPS.

A spectral algorithm for learning Hidden Markov Models

Sham M. Kakade, Tong Zhang, Daniel J. Hsu, 2008, J. Comput. Syst. Sci..

Coupled Recurrent Models for Polyphonic Music Composition

Zaïd Harchaoui, Sham M. Kakade, Dean P. Foster, 2018, ISMIR.

How to Escape Saddle Points Efficiently

Michael I. Jordan, Sham M. Kakade, Praneeth Netrapalli, 2017, ICML.

The Statistical Complexity of Interactive Decision Making pdf

Sham M. Kakade, Alexander Rakhlin, Dylan J. Foster, 2021, ArXiv.

Benign Overfitting of Constant-Stepsize SGD for Linear Regression pdf

Vladimir Braverman, Sham M. Kakade, Quanquan Gu, 2021, COLT.

Optimal Gradient-based Algorithms for Non-concave Bandit Optimization pdf

Sham M. Kakade, Qi Lei, Baihe Huang, 2021, NeurIPS.

The Benefits of Implicit Regularization from SGD in Least Squares Problems pdf

Vladimir Braverman, Sham M. Kakade, Dean P. Foster, 2021, ArXiv.

A Short Note on the Relationship of Information Gain and Eluder Dimension pdf

Sham M. Kakade, Qi Lei, Jason D. Lee, 2021, ArXiv.

Last Iterate Risk Bounds of SGD with Decaying Stepsize for Overparameterized Linear Regression pdf

Vladimir Braverman, Sham M. Kakade, Quanquan Gu, 2021, ArXiv.

Instabilities of Offline RL with Pre-Trained Neural Representation

Ruosong Wang, Ruslan Salakhutdinov, Sham M. Kakade, 2021, ICML.

Going Beyond Linear RL: Sample Efficient Neural Function Approximation pdf

Sham M. Kakade, Qi Lei, Baihe Huang, 2021, NeurIPS.

An Exponential Lower Bound for Linearly-Realizable MDPs with Constant Suboptimality Gap pdf

Sham M. Kakade, Yuanhao Wang, Ruosong Wang, 2021, NeurIPS.

Bilinear Classes: A Structural Framework for Provable Generalization in RL

Shachar Lovett, Sham M. Kakade, Simon S. Du, 2021, ICML.

Exponentiated) Stochastic Gradient Descent for L1 Constrained Problems

Ambuj Tewari, Sham M. Kakade, S. Kakade, 2008 .

Multi-View Dimensionality Reduction via Canonical Correlation Multi-View Dimensionality Reduction via Canonical Correlation Analysis Analysis Multi-View Dimensionality Reduction via Canonical Correlation Analysis Multi-View Dimensionality Reduction via Canonical Correlation Analysis Multi-View Dimen

Sham M. Kakade, Dean P. Foster, Dean Phillips Foster, 2008 .

Random Design Analysis of Ridge Regression

Sham M. Kakade, Tong Zhang, Daniel J. Hsu, 2012, COLT.