An Analysis of Ensemble Sampling
Machine Learning
2023-03-02 v2 Machine Learning
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.
Cite
@article{arxiv.2203.01303,
title = {An Analysis of Ensemble Sampling},
author = {Chao Qin and Zheng Wen and Xiuyuan Lu and Benjamin Van Roy},
journal= {arXiv preprint arXiv:2203.01303},
year = {2023}
}
Comments
[NeurIPS 2022 camera-ready version](https://openreview.net/forum?id=c6ibx0yl-aG) with improved regret bounds