NeurIPS 2022accept33 citations
An Analysis of Ensemble Sampling
Chao Qin, Zheng Wen, Xiuyuan Lu, Benjamin Van Roy
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.
Ensemble samplingThompson samplingbanditinformation theory
BibTeX
@inproceedings{
qin2022an,
title={An Analysis of Ensemble Sampling},
author={Chao Qin and Zheng Wen and Xiuyuan Lu and Benjamin Van Roy},
booktitle={Advances in Neural Information Processing Systems},
editor={Alice H. Oh and Alekh Agarwal and Danielle Belgrave and Kyunghyun Cho},
year={2022},
url={https://openreview.net/forum?id=c6ibx0yl-aG}
}