Welcome to the new version of CaltechAUTHORS. Login is currently restricted to library staff. If you notice any issues, please email coda@library.caltech.edu
Published June 22, 2022 | Published + Accepted Version
Journal Article Open

Langevin Monte Carlo for Contextual Bandits


We study the efficiency of Thompson sampling for contextual bandits. Existing Thompson sampling-based algorithms need to construct a Laplace approximation (i.e., a Gaussian distribution) of the posterior distribution, which is inefficient to sample in high dimensional applications for general covariance matrices. Moreover, the Gaussian approximation may not be a good surrogate for the posterior distribution for general reward generating functions. We propose an efficient posterior sampling algorithm, viz., Langevin Monte Carlo Thompson Sampling (LMC-TS), that uses Markov Chain Monte Carlo (MCMC) methods to directly sample from the posterior distribution in contextual bandits. Our method is computationally efficient since it only needs to perform noisy gradient descent updates without constructing the Laplace approximation of the posterior distribution. We prove that the proposed algorithm achieves the same sublinear regret bound as the best Thompson sampling algorithms for a special case of contextual bandits, viz., linear contextual bandits. We conduct experiments on both synthetic data and real-world datasets on different contextual bandit models, which demonstrates that directly sampling from the posterior is both computationally efficient and competitive in performance.

Additional Information

© 2022 by the author(s). The authors would like to thank the anonymous reviewers for their invaluable comments. PX is supported by PIMCO Postdoctoral Fellowship. AA is partially supported by Bren Named Chair Professorship at Caltech.

Attached Files

Published - xu22p.pdf

Accepted Version - 2206.11254.pdf


Files (11.4 MB)
Name Size Download all
5.8 MB Preview Download
5.6 MB Preview Download

Additional details

August 20, 2023
October 24, 2023