Timezone: »

 
Spotlight
An Analysis of Ensemble Sampling
Chao Qin · Zheng Wen · Xiuyuan Lu · Benjamin Van Roy

Tue Dec 06 05:00 PM -- 07:00 PM (PST) @
in Lightning Talks 2B-4 »

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.

Keywords: Information Theory · bandit · thompson sampling · Ensemble sampling

Author Information

Chao Qin (Columbia University)
Zheng Wen (DeepMind)
Xiuyuan Lu (DeepMind)
Benjamin Van Roy (Stanford University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors