Publications

Papers 

1. Markov Chain Variance Estimation: A Stochastic Approximation Approach

   • Preliminary version: Policy Evaluation for Variance in Average Reward Reinforcement Learning -- ICML 2024.

   • Extended version: arxiv.

   • Shubhada Agrawal, Prashanth L.A., Siva Theja Maguluri

2. Optimal Top-Two Method for Best Arm Identification and Fluid Analysis

   • Advances in Neural Information Processing Systems (NeurIPS), 2024

   • Agniv Bandyopadhyay, Sandeep Juneja, Shubhada Agrawal

3. CRIMED: Lower and Upper Bounds on Regret for Bandits with Unbounded Stochastic Corruption

• Algorithmic Learning Theory (ALT), 2024

• Shubhada Agrawal, Timothée Mathieu, Debabrota Basu, Odalric-Ambrym Maillard

4. Shift, scale and restart smaller models to estimate larger ones: Agent-based simulators in epidemiology

   • ACM SIGMETRICS Performance Evaluation Review, 2023

   • AAMAS Workshop on Autonomous Agents for Social Good, 2023 

   • Extended version available here

   • Daksh Mittal, Sandeep Juneja, Shubhada Agrawal

5. Optimal Best-Arm Identification Methods for Tail-Risk Measures

• Advances in Neural Information Processing Systems (NeurIPS), 2021

• Shubhada Agrawal, Wouter M. Koolen, Sandeep Juneja

6. Regret Minimization in Heavy-Tailed Bandits 

• 34th Annual Conference on Learning Theory (COLT), 2021

• Shubhada Agrawal, Sandeep Juneja, Wouter M. Koolen

7. Regret Minimization in Risk-Averse Bandits

• Indian Control Conference (ICC), 2021

• Shubhada Agrawal, Sandeep Juneja, Wouter M. Koolen

8. Optimal delta-Correct Best-Arm Selection for Heavy-Tailed Distributions 

• Algorithmic Learning Theory (ALT), 2020, (link) 

• Shubhada Agrawal, Sandeep Juneja, Peter Glynn

• Erratum incorporated in the arxiv version 

9. City-Scale Agent-Based Simulators for the Study of Non-pharmaceutical Interventions in the Context of the COVID-19 Epidemic

   • Journal of the Indian Institute of Science 100: 809-847,  2020

   • Shubhada Agrawal, Siddharth Bhandari, Anirban Bhattacharjee, Anand Deo, Narendra M. Dixit, Prahladh Harsha, Sandeep Juneja, Poonam Kesarwani, Aditya Krishna Swamy, Preetam Patil, Nihesh Rathod, Ramprasad Saptharishi, Sharad Shriram, Piyush Srivastava, Rajesh Sundaresan, Nidhin Koshy Vaidhiyan and Sarath Yasodharan

10. Enhanced Indexing for Risk-Averse Investors using Relaxed Second-Order Stochastic Dominance

• Journal of Optimization and Engineering 18: 407-442, 2017

• Amita Sharma, Shubhada Agrawal, Aparna Mehra

Thesis

PhD Thesis: Bandits with Heavy Tails: Algorithms, Analysis & Optimality (Bibtex) (talk)