Skip to yearly menu bar Skip to main content


Lifting the Information Ratio: An Information-Theoretic Analysis of Thompson Sampling for Contextual Bandits

Gergely Neu · Iuliia Olkhovskaia · Matteo Papini · Ludovic Schwartz

Hall J (level 1) #728

Keywords: [ thompson sampling ] [ information ratio ] [ contextual bandits ]

Abstract: We study the Bayesian regret of the renowned Thompson Sampling algorithm in contextual bandits with binary losses and adversarially-selected contexts. We adapt the information-theoretic perspective of Russo and Van Roy [2016] to the contextual setting by considering a lifted version of the information ratio defined in terms of the unknown model parameter instead of the optimal action or optimal policy as done in previous works on the same setting. This allows us to bound the regret in terms of the entropy of the prior distribution through a remarkably simple proof, and with no structural assumptions on the likelihood or the prior. The extension to priors with infinite entropy only requires a Lipschitz assumption on the log-likelihood. An interesting special case is that of logistic bandits with $d$-dimensional parameters, $K$ actions, and Lipschitz logits, for which we provide a $\tilde{O}(\sqrt{dKT})$ regret upper-bound that does not depend on the smallest slope of the sigmoid link function.

Chat is not available.