Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Sham M. Kakade

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


Oct 12, 2021
Jingfeng Wu, Difan Zou, Vladimir Braverman, Quanquan Gu, Sham M. Kakade

* 40 pages, 2 figures 

  Access Paper or Ask Questions

The Benefits of Implicit Regularization from SGD in Least Squares Problems


Aug 10, 2021
Difan Zou, Jingfeng Wu, Vladimir Braverman, Quanquan Gu, Dean P. Foster, Sham M. Kakade

* 39 pages, 1 figure 

  Access Paper or Ask Questions

Going Beyond Linear RL: Sample Efficient Neural Function Approximation


Jul 14, 2021
Baihe Huang, Kaixuan Huang, Sham M. Kakade, Jason D. Lee, Qi Lei, Runzhe Wang, Jiaqi Yang


  Access Paper or Ask Questions

Optimal Gradient-based Algorithms for Non-concave Bandit Optimization


Jul 09, 2021
Baihe Huang, Kaixuan Huang, Sham M. Kakade, Jason D. Lee, Qi Lei, Runzhe Wang, Jiaqi Yang


  Access Paper or Ask Questions

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


Jul 06, 2021
Kaixuan Huang, Sham M. Kakade, Jason D. Lee, Qi Lei


  Access Paper or Ask Questions

Benign Overfitting of Constant-Stepsize SGD for Linear Regression


Mar 23, 2021
Difan Zou, Jingfeng Wu, Vladimir Braverman, Quanquan Gu, Sham M. Kakade

* 53 pages 

  Access Paper or Ask Questions

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


Mar 23, 2021
Yuanhao Wang, Ruosong Wang, Sham M. Kakade


  Access Paper or Ask Questions

Bilinear Classes: A Structural Framework for Provable Generalization in RL


Mar 19, 2021
Simon S. Du, Sham M. Kakade, Jason D. Lee, Shachar Lovett, Gaurav Mahajan, Wen Sun, Ruosong Wang


  Access Paper or Ask Questions

Instabilities of Offline RL with Pre-Trained Neural Representation


Mar 08, 2021
Ruosong Wang, Yifan Wu, Ruslan Salakhutdinov, Sham M. Kakade


  Access Paper or Ask Questions

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


Oct 22, 2020
Ruosong Wang, Dean P. Foster, Sham M. Kakade


  Access Paper or Ask Questions

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


Jul 15, 2020
Kaiqing Zhang, Sham M. Kakade, Tamer Başar, Lin F. Yang


  Access Paper or Ask Questions

Sample-Efficient Reinforcement Learning of Undercomplete POMDPs


Jun 22, 2020
Chi Jin, Sham M. Kakade, Akshay Krishnamurthy, Qinghua Liu


  Access Paper or Ask Questions

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


May 01, 2020
Ruosong Wang, Simon S. Du, Lin F. Yang, Sham M. Kakade


  Access Paper or Ask Questions

Few-Shot Learning via Learning the Representation, Provably


Feb 21, 2020
Simon S. Du, Wei Hu, Sham M. Kakade, Jason D. Lee, Qi Lei


  Access Paper or Ask Questions

The Nonstochastic Control Problem


Jan 20, 2020
Elad Hazan, Sham M. Kakade, Karan Singh

* To appear at Algorithmic Learning Theory (ALT) 2020; small revisions from the last ver 

  Access Paper or Ask Questions

Robust Aggregation for Federated Learning


Dec 31, 2019
Krishna Pillutla, Sham M. Kakade, Zaid Harchaoui


  Access Paper or Ask Questions

Optimal Estimation of Change in a Population of Parameters


Nov 28, 2019
Ramya Korlakai Vinayak, Weihao Kong, Sham M. Kakade


  Access Paper or Ask Questions

Is a Good Representation Sufficient for Sample Efficient Reinforcement Learning?


Nov 03, 2019
Simon S. Du, Sham M. Kakade, Ruosong Wang, Lin F. Yang


  Access Paper or Ask Questions

Optimality and Approximation with Policy Gradient Methods in Markov Decision Processes


Aug 29, 2019
Alekh Agarwal, Sham M. Kakade, Jason D. Lee, Gaurav Mahajan

* Additional references and discussion of prior work 

  Access Paper or Ask Questions

Calibration, Entropy Rates, and Memory in Language Models


Jun 11, 2019
Mark Braverman, Xinyi Chen, Sham M. Kakade, Karthik Narasimhan, Cyril Zhang, Yi Zhang


  Access Paper or Ask Questions

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


Apr 29, 2019
Rong Ge, Sham M. Kakade, Rahul Kidambi, Praneeth Netrapalli

* 25 pages, 5 tables, 5 figures 

  Access Paper or Ask Questions

Online Control with Adversarial Disturbances


Feb 23, 2019
Naman Agarwal, Brian Bullins, Elad Hazan, Sham M. Kakade, Karan Singh


  Access Paper or Ask Questions

Stochastic Gradient Descent Escapes Saddle Points Efficiently


Feb 13, 2019
Chi Jin, Praneeth Netrapalli, Rong Ge, Sham M. Kakade, Michael I. Jordan


  Access Paper or Ask Questions

Maximum Likelihood Estimation for Learning Populations of Parameters


Feb 12, 2019
Ramya Korlakai Vinayak, Weihao Kong, Gregory Valiant, Sham M. Kakade


  Access Paper or Ask Questions

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


Feb 11, 2019
Chi Jin, Praneeth Netrapalli, Rong Ge, Sham M. Kakade, Michael I. Jordan


  Access Paper or Ask Questions

A Smoother Way to Train Structured Prediction Models


Feb 08, 2019
Krishna Pillutla, Vincent Roulet, Sham M. Kakade, Zaid Harchaoui

* Short version appeared in Neural Information Processing Systems (NeurIPS) 2018 

  Access Paper or Ask Questions

Provably Efficient Maximum Entropy Exploration


Dec 06, 2018
Elad Hazan, Sham M. Kakade, Karan Singh, Abby Van Soest


  Access Paper or Ask Questions