Convergence of Dirichlet Forms for MCMC Optimal Scaling with Dependent Target Distributions on Large Graphs

TL;DR

This paper uses Dirichlet form theory to analyze the convergence behavior of the Random Walk Metropolis algorithm on large graphs with dependent target distributions, providing a new perspective on high-dimensional MCMC analysis.

Contribution

It introduces a novel approach using Mosco convergence of Dirichlet forms to study RWM algorithms on large graphs with dependent targets, extending analysis to infinite-dimensional spaces.

Findings

Dirichlet form approach effectively analyzes RWM convergence.

Mosco convergence accommodates changing Hilbert spaces.

Method outperforms standard diffusion analysis in optimal scaling.

Abstract

Markov chain Monte Carlo (MCMC) algorithms have played a significant role in statistics, physics, machine learning and others, and they are the only known general and efficient approach for some high-dimensional problems. The random walk Metropolis (RWM) algorithm as the most classical MCMC algorithm, has had a great influence on the development and practice of science and engineering. The behavior of the RWM algorithm in high-dimensional problems is typically investigated through a weak convergence result of diffusion processes. In this paper, we utilize the Mosco convergence of Dirichlet forms in analyzing the RWM algorithm on large graphs, whose target distribution is the Gibbs measure that includes any probability measure satisfying a Markov property. The abstract and powerful theory of Dirichlet forms allows us to work directly and naturally on the infinite-dimensional space, and our notion of Mosco convergence allows Dirichlet forms associated with the RWM chains to lie on changing Hilbert spaces. Through the optimal scaling problem, we demonstrate the impressive strengths of the Dirichlet form approach over the standard diffusion approach.