Stochastic Multi-Armed Bandits with Control VariatesDownload PDF

21 May 2021, 20:44 (modified: 15 Jan 2022, 14:30)NeurIPS 2021 PosterReaders: Everyone
Keywords: Stochastic Multi-Armed Bandits, Variance Reduction, Control Variates
TL;DR: Multi-Armed Bandits with Control Variates
Abstract: This paper studies a new variant of the stochastic multi-armed bandits problem where auxiliary information about the arm rewards is available in the form of control variates. In many applications like queuing and wireless networks, the arm rewards are functions of some exogenous variables. The mean values of these variables are known a priori from historical data and can be used as control variates. Leveraging the theory of control variates, we obtain mean estimates with smaller variance and tighter confidence bounds. We develop an upper confidence bound based algorithm named UCB-CV and characterize the regret bounds in terms of the correlation between rewards and control variates when they follow a multivariate normal distribution. We also extend UCB-CV to other distributions using resampling methods like Jackknifing and Splitting. Experiments on synthetic problem instances validate performance guarantees of the proposed algorithms.
Supplementary Material: pdf
Code Of Conduct: I certify that all co-authors of this work have read and commit to adhering to the NeurIPS Statement on Ethics, Fairness, Inclusivity, and Code of Conduct.
13 Replies