Multi-Marginal Couplings for Metropolis-Hastings

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Phan, Buu, Flamich, Gergely, Khisti, Ashish, Asoodeh, Shahab
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909038440087552
author Phan, Buu
Flamich, Gergely
Khisti, Ashish
Asoodeh, Shahab
author_facet Phan, Buu
Flamich, Gergely
Khisti, Ashish
Asoodeh, Shahab
contents Convergence diagnosis for Markov chain Monte Carlo is a matter of fundamental importance in computational statistics: it determines the resources allocated to a particular sampling problem and influences the practitioner's view of the quality of estimates obtained from a Markov chain. Motivated by this, we contribute to the emerging class of coupling-based convergence diagnostic algorithms. Concretely, we study coupling multiple Metropolis-Hastings chains using multi-marginal coupling. We introduce a natural objective for this setting and establish lower and upper bounds by drawing connections to list-level distribution coupling and distributed pairwise-matching problems. This analysis ultimately leads to a shared-randomness Poisson Monte Carlo construction for coupling multiple Markov chains. In this process, we avoid a key dimension-dependent bottleneck in the runtime complexity of classical Poisson Monte Carlo by developing an adaptive rule for updating the point process, yielding significant gains in high-dimensional settings. Experiments on grand couplings of Markov chains show that our methods improve coalescence rates across dimensions, reducing meeting times by up to 50% compared with existing baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2605_12807
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Multi-Marginal Couplings for Metropolis-Hastings
Phan, Buu
Flamich, Gergely
Khisti, Ashish
Asoodeh, Shahab
Computation
Information Theory
Convergence diagnosis for Markov chain Monte Carlo is a matter of fundamental importance in computational statistics: it determines the resources allocated to a particular sampling problem and influences the practitioner's view of the quality of estimates obtained from a Markov chain. Motivated by this, we contribute to the emerging class of coupling-based convergence diagnostic algorithms. Concretely, we study coupling multiple Metropolis-Hastings chains using multi-marginal coupling. We introduce a natural objective for this setting and establish lower and upper bounds by drawing connections to list-level distribution coupling and distributed pairwise-matching problems. This analysis ultimately leads to a shared-randomness Poisson Monte Carlo construction for coupling multiple Markov chains. In this process, we avoid a key dimension-dependent bottleneck in the runtime complexity of classical Poisson Monte Carlo by developing an adaptive rule for updating the point process, yielding significant gains in high-dimensional settings. Experiments on grand couplings of Markov chains show that our methods improve coalescence rates across dimensions, reducing meeting times by up to 50% compared with existing baselines.
title Multi-Marginal Couplings for Metropolis-Hastings
topic Computation
Information Theory
url https://arxiv.org/abs/2605.12807