An Information-Theoretic Analysis for Thompson Sampling with Many Actions
Shi Dong · Benjamin Van Roy

Thu Dec 6th 05:00 -- 07:00 PM @ Room 517 AB #159

Information-theoretic Bayesian regret bounds of Russo and Van Roy capture the dependence of regret on prior uncertainty. However, this dependence is through entropy, which can become arbitrarily large as the number of actions increases. We establish new bounds that depend instead on a notion of rate-distortion. Among other things, this allows us to recover through information-theoretic arguments a near-optimal bound for the linear bandit. We also offer a bound for the logistic bandit that dramatically improves on the best previously available, though this bound depends on an information-theoretic statistic that we have only been able to quantify via computation.

Author Information

Shi Dong (Stanford University)
Benjamin Van Roy (Stanford University)

More from the Same Authors