Skip to yearly menu bar Skip to main content


Poster

An Analysis of Ensemble Sampling

Chao Qin · Zheng Wen · Xiuyuan Lu · Benjamin Van Roy

Hall J (level 1) #933

Keywords: [ Ensemble sampling ] [ Information Theory ] [ bandit ] [ thompson sampling ]


Abstract:

Ensemble sampling serves as a practical approximation to Thompson sampling when maintaining an exact posterior distribution over model parameters is computationally intractable. In this paper, we establish a regret bound that ensures desirable behavior when ensemble sampling is applied to the linear bandit problem. This represents the first rigorous regret analysis of ensemble sampling and is made possible by leveraging information-theoretic concepts and novel analytic techniques that may prove useful beyond the scope of this paper.

Chat is not available.