Dynamic Batch Learning in High-Dimensional Sparse Linear Contextual Bandits

Abstract

We study the problem of dynamic batch learning in high-dimensional sparse linear contextual bandits, where a decision maker, under a given maximum-number-of-batch constraint and only able to observe rewards at the end of each batch, can dynamically decide how many individuals to include in the next batch (at the end of the current batch) and what personalized action-selection scheme to adopt within each batch. Such batch constraints are ubiquitous in a variety of practical contexts, including personalized product offerings in marketing and medical treatment selection in clinical trials. We characterize the fundamental learning limit in this problem via a regret lower bound and provide a matching upper bound (up to log factors), thus prescribing an optimal scheme for this problem. To the best of our knowledge, our work provides the first inroad into a theoretical understanding of dynamic batch learning in high-dimensional sparse linear contextual bandits. Notably, even a special case of our result -- when no batch constraint is present -- yields that the simple exploration-free algorithm using the LASSO estimator already achieves the minimax optimal regret bound for standard online learning in high-dimensional linear contextual bandits (for the no-margin case), a result that appears unknown in the emerging literature of high-dimensional contextual bandits.

arXiv comment41 pages

References in corpus (14)

• Simultaneous analysis of Lasso and Dantzig selector
• Thompson Sampling for Contextual Bandits with Linear Payoffs
• Batched bandit problems
• Interpreting Blackbox Models via Model Extraction
• Nonparametric Bandits with Covariates
• Confounding-Robust Policy Improvement
• Sequential Batch Learning in Finite-Action Linear Contextual Bandits
• Doubly-Robust Lasso Bandit
• Efficient Smoothed Concomitant Lasso Estimation for High Dimensional Regression
• A Practical Method for Solving Contextual Bandit Problems Using Decision Trees
• High Dimensional Sparse Econometric Models: An Introduction
• Rebounding Bandits for Modeling Satiation Effects
• A Bit Better? Quantifying Information for Bandit Learning
• Bandit Theory meets Compressed Sensing for high dimensional Stochastic Linear Bandit

Cited by in corpus (4)

• Generalized Linear Bandits with Local Differential Privacy
• Online Sparse Reinforcement Learning
• Regret Minimization in Isotonic, Heavy-Tailed Contextual Bandits via Adaptive Confidence Bands
• Information Directed Sampling for Sparse Linear Bandits