MCMC-driven learning
This work provides a foundational synthesis for researchers in computational statistics and machine learning, though it is incremental as it consolidates existing approaches rather than introducing new ones.
The paper tackles the problem of unifying diverse methods at the intersection of Markov chain Monte Carlo (MCMC) and machine learning, such as black-box variational inference and adaptive MCMC, into a common framework to enable translation and generalization of theories and methods.
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 learning$\unicode{x2014}$which 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 more$\unicode{x2014}$within one common framework. By doing so, the theory and methods developed for each may be translated and generalized.