MCMC-driven learning
Machine Learning
2024-02-16 v1 Machine Learning
Statistics Theory
Computation
Statistics Theory
Abstract
This paper is intended to appear as a chapter for the Handbook of Markov Chain Monte Carlo. The goal of this chapter is to unify various problems at the intersection of Markov chain Monte Carlo (MCMC) and machine learningwhich includes black-box variational inference, adaptive MCMC, normalizing flow construction and transport-assisted MCMC, surrogate-likelihood MCMC, coreset construction for MCMC with big data, Markov chain gradient descent, Markovian score climbing, and morewithin one common framework. By doing so, the theory and methods developed for each may be translated and generalized.
Cite
@article{arxiv.2402.09598,
title = {MCMC-driven learning},
author = {Alexandre Bouchard-Côté and Trevor Campbell and Geoff Pleiss and Nikola Surjanovic},
journal= {arXiv preprint arXiv:2402.09598},
year = {2024}
}