Analysis of Multiple-try Metropolis via Poincaré inequalities

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Caprio, Rocco, Power, Sam, Wang, Andi Q.
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912714280927232
author Caprio, Rocco
Power, Sam
Wang, Andi Q.
author_facet Caprio, Rocco
Power, Sam
Wang, Andi Q.
contents We study the Multiple-try Metropolis algorithm using the framework of Poincaré inequalities. We describe the Multiple-try Metropolis as an auxiliary variable implementation of a resampling approximation to an ideal Metropolis--Hastings algorithm. Under suitable moment conditions on the importance weights, we derive explicit Poincaré comparison results between the Multiple-try algorithm and the ideal algorithm. We characterize the spectral gap of the latter, and finally in the Gaussian case prove explicit non-asymptotic convergence bounds for Multiple-try Metropolis by comparison.
format Preprint
id arxiv_https___arxiv_org_abs_2504_18409
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Analysis of Multiple-try Metropolis via Poincaré inequalities
Caprio, Rocco
Power, Sam
Wang, Andi Q.
Computation
Probability
We study the Multiple-try Metropolis algorithm using the framework of Poincaré inequalities. We describe the Multiple-try Metropolis as an auxiliary variable implementation of a resampling approximation to an ideal Metropolis--Hastings algorithm. Under suitable moment conditions on the importance weights, we derive explicit Poincaré comparison results between the Multiple-try algorithm and the ideal algorithm. We characterize the spectral gap of the latter, and finally in the Gaussian case prove explicit non-asymptotic convergence bounds for Multiple-try Metropolis by comparison.
title Analysis of Multiple-try Metropolis via Poincaré inequalities
topic Computation
Probability
url https://arxiv.org/abs/2504.18409