English

Thompson Sampling with Approximate Inference

Machine Learning 2020-01-16 v2 Machine Learning

Abstract

We study the effects of approximate inference on the performance of Thompson sampling in the kk-armed bandit problems. Thompson sampling is a successful algorithm for online decision-making but requires posterior inference, which often must be approximated in practice. We show that even small constant inference error (in α\alpha-divergence) can lead to poor performance (linear regret) due to under-exploration (for α<1\alpha<1) or over-exploration (for α>0\alpha>0) by the approximation. While for α>0\alpha > 0 this is unavoidable, for α0\alpha \leq 0 the regret can be improved by adding a small amount of forced exploration even when the inference error is a large constant.

Keywords

Cite

@article{arxiv.1908.04970,
  title  = {Thompson Sampling with Approximate Inference},
  author = {My Phan and Yasin Abbasi-Yadkori and Justin Domke},
  journal= {arXiv preprint arXiv:1908.04970},
  year   = {2020}
}
R2 v1 2026-06-23T10:47:05.149Z