English

Reinforcement Learning for Adaptive MCMC

Computation 2024-05-24 v1 Machine Learning

Abstract

An informal observation, made by several authors, is that the adaptive design of a Markov transition kernel has the flavour of a reinforcement learning task. Yet, to-date it has remained unclear how to actually exploit modern reinforcement learning technologies for adaptive MCMC. The aim of this paper is to set out a general framework, called Reinforcement Learning Metropolis--Hastings, that is theoretically supported and empirically validated. Our principal focus is on learning fast-mixing Metropolis--Hastings transition kernels, which we cast as deterministic policies and optimise via a policy gradient. Control of the learning rate provably ensures conditions for ergodicity are satisfied. The methodology is used to construct a gradient-free sampler that out-performs a popular gradient-free adaptive Metropolis--Hastings algorithm on 90%\approx 90 \% of tasks in the PosteriorDB benchmark.

Keywords

Cite

@article{arxiv.2405.13574,
  title  = {Reinforcement Learning for Adaptive MCMC},
  author = {Congye Wang and Wilson Chen and Heishiro Kanagawa and Chris. J. Oates},
  journal= {arXiv preprint arXiv:2405.13574},
  year   = {2024}
}
R2 v1 2026-06-28T16:35:37.071Z