Spectral gap bounds for reversible hybrid Gibbs chains

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Qin, Qian, Ju, Nianqiao, Wang, Guanyang
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915206779633664
author Qin, Qian
Ju, Nianqiao
Wang, Guanyang
author_facet Qin, Qian
Ju, Nianqiao
Wang, Guanyang
contents Hybrid Gibbs samplers represent a prominent class of approximated Gibbs algorithms that utilize Markov chains to approximate conditional distributions, with the Metropolis-within-Gibbs algorithm standing out as a well-known example. Despite their widespread use in both statistical and non-statistical applications, little is known about their convergence properties. This article introduces novel methods for establishing bounds on the convergence rates of certain reversible hybrid Gibbs samplers. In particular, we examine the convergence characteristics of hybrid random-scan Gibbs algorithms. Our analysis reveals that the absolute spectral gap of a hybrid Gibbs chain can be bounded based on the absolute spectral gap of the exact Gibbs chain and the absolute spectral gaps of the Markov chains employed for conditional distribution approximations. We also provide a convergence bound of similar flavors for hybrid data augmentation algorithms, extending existing works on the topic. The general bounds are applied to three examples: a random-scan Metropolis-within-Gibbs sampler, random-scan Gibbs samplers with block updates, and a hybrid slice sampler.
format Preprint
id arxiv_https___arxiv_org_abs_2312_12782
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Spectral gap bounds for reversible hybrid Gibbs chains
Qin, Qian
Ju, Nianqiao
Wang, Guanyang
Statistics Theory
Probability
60J05
Hybrid Gibbs samplers represent a prominent class of approximated Gibbs algorithms that utilize Markov chains to approximate conditional distributions, with the Metropolis-within-Gibbs algorithm standing out as a well-known example. Despite their widespread use in both statistical and non-statistical applications, little is known about their convergence properties. This article introduces novel methods for establishing bounds on the convergence rates of certain reversible hybrid Gibbs samplers. In particular, we examine the convergence characteristics of hybrid random-scan Gibbs algorithms. Our analysis reveals that the absolute spectral gap of a hybrid Gibbs chain can be bounded based on the absolute spectral gap of the exact Gibbs chain and the absolute spectral gaps of the Markov chains employed for conditional distribution approximations. We also provide a convergence bound of similar flavors for hybrid data augmentation algorithms, extending existing works on the topic. The general bounds are applied to three examples: a random-scan Metropolis-within-Gibbs sampler, random-scan Gibbs samplers with block updates, and a hybrid slice sampler.
title Spectral gap bounds for reversible hybrid Gibbs chains
topic Statistics Theory
Probability
60J05
url https://arxiv.org/abs/2312.12782