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 Sanjay Shakkottai

Episodic Bandits with Stochastic Experts


Jul 07, 2021
Nihal Sharma, Soumya Basu, Karthikeyan Shanmugam, Sanjay Shakkottai


  Access Paper or Ask Questions

Finite-Sample Analysis of Off-Policy TD-Learning via Generalized Bellman Operators


Jun 24, 2021
Zaiwei Chen, Siva Theja Maguluri, Sanjay Shakkottai, Karthikeyan Shanmugam


  Access Paper or Ask Questions

Does Optimal Source Task Performance Imply Optimal Pre-training for a Target Task?


Jun 21, 2021
Steven Gutstein, Brent Lance, Sanjay Shakkottai


  Access Paper or Ask Questions

Job Dispatching Policies for Queueing Systems with Unknown Service Rates


Jun 10, 2021
Tuhinangshu Choudhury, Gauri Joshi, Weina Wang, Sanjay Shakkottai


  Access Paper or Ask Questions

Combinatorial Blocking Bandits with Stochastic Delays


May 22, 2021
Alexia Atsidakou, Orestis Papadigenopoulos, Soumya Basu, Constantine Caramanis, Sanjay Shakkottai

* International Conference on Machine Learning, ICML'21 

  Access Paper or Ask Questions

Regret Bounds for Stochastic Shortest Path Problems with Linear Function Approximation


May 04, 2021
Daniel Vial, Advait Parulekar, Sanjay Shakkottai, R. Srikant


  Access Paper or Ask Questions

Linear Bandit Algorithms with Sublinear Time Complexity


Mar 03, 2021
Shuo Yang, Tongzheng Ren, Sanjay Shakkottai, Eric Price, Inderjit S. Dhillon, Sujay Sanghavi


  Access Paper or Ask Questions

Exploiting Shared Representations for Personalized Federated Learning


Feb 14, 2021
Liam Collins, Hamed Hassani, Aryan Mokhtari, Sanjay Shakkottai


  Access Paper or Ask Questions

A Lyapunov Theory for Finite-Sample Guarantees of Asynchronous Q-Learning and TD-Learning Variants


Feb 02, 2021
Zaiwei Chen, Siva Theja Maguluri, Sanjay Shakkottai, Karthikeyan Shanmugam


  Access Paper or Ask Questions

One-bit feedback is sufficient for upper confidence bound policies


Dec 04, 2020
Daniel Vial, Sanjay Shakkottai, R. Srikant


  Access Paper or Ask Questions

Stochastic Linear Bandits with Protected Subspace


Nov 02, 2020
Advait Parulekar, Soumya Basu, Aditya Gopalan, Karthikeyan Shanmugam, Sanjay Shakkottai


  Access Paper or Ask Questions

Why Does MAML Outperform ERM? An Optimization Perspective


Oct 27, 2020
Liam Collins, Aryan Mokhtari, Sanjay Shakkottai


  Access Paper or Ask Questions

Hellinger KL-UCB based Bandit Algorithms for Markovian and i.i.d. Settings


Sep 14, 2020
Arghyadip Roy, Sanjay Shakkottai, R. Srikant


  Access Paper or Ask Questions

Robust Multi-Agent Multi-Armed Bandits


Jul 07, 2020
Daniel Vial, Sanjay Shakkottai, R. Srikant


  Access Paper or Ask Questions

Multi-Agent Low-Dimensional Linear Bandits


Jul 02, 2020
Ronshee Chawla, Abishek Sankararaman, Sanjay Shakkottai


  Access Paper or Ask Questions

Contextual Blocking Bandits


Mar 06, 2020
Soumya Basu, Orestis Papadigenopoulos, Constantine Caramanis, Sanjay Shakkottai


  Access Paper or Ask Questions

Warm Starting Bandits with Side Information from Confounded Data


Feb 19, 2020
Nihal Sharma, Soumya Basu, Karthikeyan Shanmugam, Sanjay Shakkottai


  Access Paper or Ask Questions

The Gossiping Insert-Eliminate Algorithm for Multi-Agent Bandits


Feb 12, 2020
Ronshee Chawla, Abishek Sankararaman, Ayalvadi Ganesh, Sanjay Shakkottai

* To Appear in AISTATS 2020. The first two authors contributed equally 

  Access Paper or Ask Questions

Distribution-Agnostic Model-Agnostic Meta-Learning


Feb 12, 2020
Liam Collins, Aryan Mokhtari, Sanjay Shakkottai


  Access Paper or Ask Questions

Finite-Sample Analysis of Stochastic Approximation Using Smooth Convex Envelopes


Feb 10, 2020
Zaiwei Chen, Siva Theja Maguluri, Sanjay Shakkottai, Karthikeyan Shanmugam

* Total 27 pages, main paper 13 pages, references 2 pages, Appendix 12 pages 

  Access Paper or Ask Questions

Social Learning in Multi Agent Multi Armed Bandits


Nov 05, 2019
Abishek Sankararaman, Ayalvadi Ganesh, Sanjay Shakkottai

* Minor Corrections from before 

  Access Paper or Ask Questions

Optimistic Optimization for Statistical Model Checking with Regret Bounds


Nov 04, 2019
Negin Musavi, Dawei Sun, Sayan Mitra, Geir Dullerud, Sanjay Shakkottai

* 24 pages, 7 figures 

  Access Paper or Ask Questions

Mix and Match: An Optimistic Tree-Search Approach for Learning Models from Mixture Distributions


Aug 23, 2019
Matthew Faw, Rajat Sen, Karthikeyan Shanmugam, Constantine Caramanis, Sanjay Shakkottai


  Access Paper or Ask Questions

Blocking Bandits


Jul 27, 2019
Soumya Basu, Rajat Sen, Sujay Sanghavi, Sanjay Shakkottai


  Access Paper or Ask Questions

Noisy Blackbox Optimization with Multi-Fidelity Queries: A Tree Search Approach


Oct 24, 2018
Rajat Sen, Kirthevasan Kandasamy, Sanjay Shakkottai

* 18 pages, 9 Figures 

  Access Paper or Ask Questions