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 Rahul Kidambi

Mitigating Covariate Shift in Imitation Learning via Offline Data Without Great Coverage

Jun 14, 2021
Jonathan D. Chang, Masatoshi Uehara, Dhruv Sreenivas, Rahul Kidambi, Wen Sun

* 42 pages, 5 figures, 7 tables 

  Access Paper or Ask Questions

Making Paper Reviewing Robust to Bid Manipulation Attacks

Feb 22, 2021
Ruihan Wu, Chuan Guo, Felix Wu, Rahul Kidambi, Laurens van der Maaten, Kilian Q. Weinberger

  Access Paper or Ask Questions

Optimism is All You Need: Model-Based Imitation Learning From Observation Alone

Feb 22, 2021
Rahul Kidambi, Jonathan Chang, Wen Sun

* 25 pages, 3 figures, 1 tabular column 

  Access Paper or Ask Questions

Top-$k$ eXtreme Contextual Bandits with Arm Hierarchy

Feb 15, 2021
Rajat Sen, Alexander Rakhlin, Lexing Ying, Rahul Kidambi, Dean Foster, Daniel Hill, Inderjit Dhillon

  Access Paper or Ask Questions

MOReL : Model-Based Offline Reinforcement Learning

May 12, 2020
Rahul Kidambi, Aravind Rajeswaran, Praneeth Netrapalli, Thorsten Joachims

* First two authors contributed equally. 18 pages of main text. 2 sections of appendix 

  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

On the insufficiency of existing momentum schemes for Stochastic Optimization

Jul 31, 2018
Rahul Kidambi, Praneeth Netrapalli, Prateek Jain, Sham M. Kakade

* 28 pages, 10 figures. Updated acknowledgements. Appeared as an oral presentation at International Conference on Learning Representations (ICLR), 2018. Code implementing the ASGD method can be found at 

  Access Paper or Ask Questions

Accelerating Stochastic Gradient Descent For Least Squares Regression

Jul 31, 2018
Prateek Jain, Sham M. Kakade, Rahul Kidambi, Praneeth Netrapalli, Aaron Sidford

* 54 pages, 3 figures, 1 table; updated acknowledgements, minor title change. Paper appeared in the proceedings of the Conference on Learning Theory (COLT), 2018 

  Access Paper or Ask Questions

Parallelizing Stochastic Gradient Descent for Least Squares Regression: mini-batching, averaging, and model misspecification

Jul 31, 2018
Prateek Jain, Sham M. Kakade, Rahul Kidambi, Praneeth Netrapalli, Aaron Sidford

* 39 pages. Published in the Journal of Machine Learning Research (JMLR) 

  Access Paper or Ask Questions

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

Jul 21, 2018
Prateek Jain, Sham M. Kakade, Rahul Kidambi, Praneeth Netrapalli, Venkata Krishna Pillutla, Aaron Sidford

* Lemma 1 has been updated in v2 

  Access Paper or Ask Questions

Leverage Score Sampling for Faster Accelerated Regression and ERM

Nov 22, 2017
Naman Agarwal, Sham Kakade, Rahul Kidambi, Yin Tat Lee, Praneeth Netrapalli, Aaron Sidford

  Access Paper or Ask Questions

Efficient Estimation of Generalization Error and Bias-Variance Components of Ensembles

Nov 15, 2017
Dhruv Mahajan, Vivek Gupta, S Sathiya Keerthi, Sellamanickam Sundararajan, Shravan Narayanamurthy, Rahul Kidambi

* 12 Pages, 4 Figures, 12 Pages, Under Review in SDM 2018 

  Access Paper or Ask Questions

Submodular Hamming Metrics

Nov 06, 2015
Jennifer Gillenwater, Rishabh Iyer, Bethany Lusch, Rahul Kidambi, Jeff Bilmes

* 15 pages, 1 figure, a short version of this will appear in the NIPS 2015 conference 

  Access Paper or Ask Questions

A Quantitative Evaluation Framework for Missing Value Imputation Algorithms

Nov 10, 2013
Vinod Nair, Rahul Kidambi, Sundararajan Sellamanickam, S. Sathiya Keerthi, Johannes Gehrke, Vijay Narayanan

* 9 pages 

  Access Paper or Ask Questions

A Structured Prediction Approach for Missing Value Imputation

Nov 09, 2013
Rahul Kidambi, Vinod Nair, Sundararajan Sellamanickam, S. Sathiya Keerthi

* 9 Pages 

  Access Paper or Ask Questions