80 citations · 177 across the 25 of their papers we have counts for
28 papers
Adaptive inference for functionals of M-estimands
James Leiner, Aurélien Bibaut, Nathan Kallus +2
Reinforcement learning and contextual bandit algorithms have become increasingly common in sequential decision-making applications. When these methods are deployed in high-stakes d…
Bandit Simulation for Average Reward Inference
Samya Praharaj, Chih-Yu Chang, Koulik Khamaru +1
Multi-arm bandit algorithms are increasingly used in online platforms, clinical trials, and social science experiments, but valid statistical inference on their performance remains…
Stabilizing Bandits using Regularization: Precise Regret and A Quantitative Central Limit Theorem
Budhaditya Halder, Ishan Sengupta, Koustav Chowdhury +2
Statistical inference with bandit data presents fundamental challenges owing to adaptive sampling, which violates the independence assumptions underlying classical asymptotic theor…
Efficient Inference after Directionally Stable Adaptive Experiments
Zikai Shen, Houssam Zenati, Nathan Kallus +3
We study inference on scalar-valued pathwise differentiable targets after adaptive data collection, such as a bandit algorithm. We introduce a novel target-specific condition, dire…
Avoiding the Price of Adaptivity: Inference in Linear Contextual Bandits via Stability
Samya Praharaj, Koulik Khamaru
Statistical inference in contextual bandits is challenging due to the adaptive, non-i.i.d. nature of the data. A growing body of work shows that classical least-squares inference c…
On Instability of Minimax Optimal Optimism-Based Bandit Algorithms
Samya Praharaj, Koulik Khamaru
Statistical inference from data generated by multi-armed bandit (MAB) algorithms is challenging due to their adaptive, non-i.i.d. nature. A classical manifestation is that sample a…
Design Stability in Adaptive Experiments: Implications for Treatment Effect Estimation
Saikat Sengupta, Koulik Khamaru, Suvrojit Ghosh +1
We study the problem of estimating the average treatment effect (ATE) under sequentially adaptive treatment assignment mechanisms. In contrast to classical completely randomized de…
Stable Thompson Sampling: Valid Inference via Variance Inflation
Budhaditya Halder, Shubhayan Pan, Koulik Khamaru
We consider the problem of statistical inference when the data is collected via a Thompson Sampling-type algorithm. While Thompson Sampling (TS) is known to be both asymptotically…
UCB algorithms for multi-armed bandits: Precise regret and adaptive inference
Qiyang Han, Koulik Khamaru, Cun-Hui Zhang
Upper Confidence Bound (UCB) algorithms are a widely-used class of sequential algorithms for the -armed bandit problem. Despite extensive research over the past decades aimed at…
PICS: A sequential approach to obtain optimal designs for non-linear models leveraging closed-form solutions for faster convergence
Suvrojit Ghosh, Koulik Khamaru, Tirthankar Dasgupta
D-Optimal designs for estimating parameters of response models are derived by maximizing the determinant of the Fisher information matrix. For non-linear models, the Fisher informa…
Inference with the Upper Confidence Bound Algorithm
Koulik Khamaru, Cun-Hui Zhang
In this paper, we discuss the asymptotic behavior of the Upper Confidence Bound (UCB) algorithm in the context of multiarmed bandit problems and discuss its implication in downstre…
Uncertainty Quantification With Multiple Sources
Mufang Ying, Wenge Guo, Koulik Khamaru +1
Weighted conformal prediction (WCP) has been commonly used to quantify prediction uncertainty under covariate shift. However, the effectiveness of WCP relies heavily on the degree…
Stochastic Optimization with Constraints: A Non-asymptotic Instance-Dependent Analysis
Koulik Khamaru
We consider the problem of stochastic convex optimization under convex constraints. We analyze the behavior of a natural variance reduced proximal gradient (VRPG) algorithm for thi…
Statistical Limits of Adaptive Linear Models: Low-Dimensional Estimation and Inference
Licong Lin, Mufang Ying, Suvrojit Ghosh +2
Estimation and inference in statistics pose significant challenges when data are collected adaptively. Even in linear models, the Ordinary Least Squares (OLS) estimator may fail to…
Adaptive Linear Estimating Equations
Mufang Ying, Koulik Khamaru, Cun-Hui Zhang
Sequential data collection has emerged as a widely adopted technique for enhancing the efficiency of data gathering processes. Despite its advantages, such data collection mechanis…
Semi-parametric inference based on adaptively collected data
Licong Lin, Koulik Khamaru, Martin J. Wainwright
Many standard estimators, when applied to adaptively collected data, fail to be asymptotically normal, thereby complicating the construction of confidence intervals. We address thi…
Instance-Dependent Confidence and Early Stopping for Reinforcement Learning
Koulik Khamaru, Eric Xia, Martin J. Wainwright +1
Various algorithms for reinforcement learning (RL) exhibit dramatic variation in their convergence rates as a function of problem structure. Such problem-dependent behavior is not…
Optimal variance-reduced stochastic approximation in Banach spaces
Wenlong Mou, Koulik Khamaru, Martin J. Wainwright +2
We study the problem of estimating the fixed point of a contractive operator defined on a separable Banach space. Focusing on a stochastic query model that provides noisy evaluatio…
Near-optimal inference in adaptive linear regression
Koulik Khamaru, Yash Deshpande, Tor Lattimore +2
When data is collected in an adaptive manner, even simple methods like ordinary least squares can exhibit non-normal asymptotic behavior. As an undesirable consequence, hypothesis…
Instance-optimality in optimal value estimation: Adaptivity via variance-reduced Q-learning
Koulik Khamaru, Eric Xia, Martin J. Wainwright +1
Various algorithms in reinforcement learning exhibit dramatic variability in their convergence rates and ultimate accuracy as a function of the problem structure. Such instance-spe…
Instability, Computational Efficiency and Statistical Accuracy
Nhat Ho, Koulik Khamaru, Raaz Dwivedi +3
Many statistical estimators are defined as the fixed point of a data-dependent operator, with estimators based on minimizing a cost function being an important special case. The li…
Is Temporal Difference Learning Optimal? An Instance-Dependent Analysis
Koulik Khamaru, Ashwin Pananjady, Feng Ruan +2
We address the problem of policy evaluation in discounted Markov decision processes, and provide instance-dependent guarantees on the -error under a generative model.…
Sharp Analysis of Expectation-Maximization for Weakly Identifiable Models
Raaz Dwivedi, Nhat Ho, Koulik Khamaru +3
We study a class of weakly identifiable location-scale mixture models for which the maximum likelihood estimates based on i.i.d. samples are known to have lower accuracy than t…
Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systems
Dhruv Malik, Ashwin Pananjady, Kush Bhatia +3
We study derivative-free methods for policy optimization over the class of linear policies. We focus on characterizing the convergence rate of these methods when applied to linear-…