33 citations · 51 across the 14 of their papers we have counts for
17 papers
Reliable Scale-Free Bandits via Empirical Likelihood
Pratham Gupta, Alhad Sethi, Shubhada Agrawal
We study stochastic bandits without knowledge of reward scales or tail parameters. Almost-sure regret guarantees describe eventual learning but do not quantify expected performance…
Best Arm Identification for Bandits with Shifting Means
Lukas Zierahn, Wouter M. Koolen, Shubhada Agrawal +2
We study the best arm identification problem in a stochastic environment with a novel form of adversarial perturbations, which we coin Shifting Means. While classically the mean re…
Cover meets Robbins while Betting on Bounded Data: Regret and Almost Sure Regret
Shubhada Agrawal, Aaditya Ramdas
Consider betting against a sequence of -valued observations using bets that are fair if the data have a conditional mean . Cover's universal portfolio algorit…
Regret Tail Characterization of Optimal Bandit Algorithms with Generic Rewards
Subhodip Panda, Shubhada Agrawal
We study the tail behavior of regret in stochastic multi-armed bandits for algorithms that are asymptotically optimal in expectation. While minimizing expected regret is the classi…
Dual Representation of Minimum Divergence Under Integral Constraints
Shubhanshu Shekhar, Shubhada Agrawal
Minimum divergence problems under integral constraints appear throughout statistics and probability, including sequential inference, bandit theory, and distributionally robust opti…
Asymptotically Optimal Sequential Testing with Markovian Data
Alhad Sethi, Kavali Sofia Sagar, Shubhada Agrawal +2
We study one-sided and -correct sequential hypothesis testing for data generated by an ergodic, finite-state Markov chain. The null hypothesis is that the unknown transition mat…
Almost sure null bankruptcy of testing-by-betting strategies
Hongjian Wang, Shubhada Agrawal, Aaditya Ramdas
The bounded mean betting procedure serves as a crucial interface between the domains of (1) sequential, anytime-valid statistical inference, and (2) online learning and portfolio s…
Eventually LIL Regret: Almost Sure Regret for a sub-Gaussian Mixture on Unbounded Data
Shubhada Agrawal, Aaditya Ramdas
We prove that a classic sub-Gaussian mixture proposed by Robbins in a stochastic setting actually satisfies a path-wise (deterministic) regret bound. For every path in a natural ``…
How to Backdoor Image Knowledge Distillation
Qian Ma, Chen Wu, Prasenjit Mitra +1
Knowledge distillation is widely used to transfer behavior from a large teacher model to a smaller student. It is often assumed to be safe when the teacher is clean, because classi…
Optimal Top-Two Method for Best Arm Identification and Fluid Analysis
Agniv Bandyopadhyay, Sandeep Juneja, Shubhada Agrawal
Top- methods have become popular in solving the best arm identification (BAI) problem. The best arm, or the arm with the largest mean amongst finitely many, is identified throug…
CRIMED: Lower and Upper Bounds on Regret for Bandits with Unbounded Stochastic Corruption
Shubhada Agrawal, Timothée Mathieu, Debabrota Basu +1
We investigate the regret-minimisation problem in a multi-armed bandit setting with arbitrary corruptions. Similar to the classical setup, the agent receives rewards generated inde…
Optimal Best-Arm Identification in Bandits with Access to Offline Data
Shubhada Agrawal, Sandeep Juneja, Karthikeyan Shanmugam +1
Learning paradigms based purely on offline data as well as those based solely on sequential online learning have been well-studied in the literature. In this paper, we consider com…
Agent Based Simulators for Epidemic Modelling: Simulating Larger Models Using Smaller Ones
Daksh Mittal, Sandeep Juneja
Agent-based simulators (ABS) are a popular epidemiological modelling tool to study the impact of various non-pharmaceutical interventions in managing an epidemic in a city (or a re…
Regret Minimization in Heavy-Tailed Bandits
Shubhada Agrawal, Sandeep Juneja, Wouter M. Koolen
We revisit the classic regret-minimization problem in the stochastic multi-armed bandit setting when the arm-distributions are allowed to be heavy-tailed. Regret minimization has b…
City-Scale Agent-Based Simulators for the Study of Non-Pharmaceutical Interventions in the Context of the COVID-19 Epidemic
Shubhada Agrawal, Siddharth Bhandari, Anirban Bhattacharjee +14
We highlight the usefulness of city-scale agent-based simulators in studying various non-pharmaceutical interventions to manage an evolving pandemic. We ground our studies in the c…
Optimal Best-Arm Identification Methods for Tail-Risk Measures
Shubhada Agrawal, Wouter M. Koolen, Sandeep Juneja
Conditional value-at-risk (CVaR) and value-at-risk (VaR) are popular tail-risk measures in finance and insurance industries as well as in highly reliable, safety-critical uncertain…
Optimal -Correct Best-Arm Selection for Heavy-Tailed Distributions
Shubhada Agrawal, Sandeep Juneja, Peter Glynn
Given a finite set of unknown distributions or arms that can be sampled, we consider the problem of identifying the one with the maximum mean using a -correct algorithm (an adap…