Markov chain Monte Carlo without evaluating the target: an auxiliary variable approach

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yuan, Wei, Wang, Guanyang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912221127245824
author Yuan, Wei
Wang, Guanyang
author_facet Yuan, Wei
Wang, Guanyang
contents In sampling tasks, it is common for target distributions to be known up to a normalizing constant. However, in many situations, even evaluating the unnormalized distribution can be costly or infeasible. This issue arises in scenarios such as sampling from the Bayesian posterior for tall datasets and the 'doubly-intractable' distributions. In this paper, we begin by observing that seemingly different Markov chain Monte Carlo (MCMC) algorithms, such as the exchange algorithm, PoissonMH, and TunaMH, can be unified under a simple common procedure. We then extend this procedure into a novel framework that allows the use of auxiliary variables in both the proposal and the acceptance-rejection step. Several new MCMC algorithms emerge from this framework that utilize estimated gradients to guide the proposal moves. They have demonstrated significantly better performance than existing methods on both synthetic and real datasets. Additionally, we develop the theory of the new framework and apply it to existing algorithms to simplify and extend their results.
format Preprint
id arxiv_https___arxiv_org_abs_2406_05242
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Markov chain Monte Carlo without evaluating the target: an auxiliary variable approach
Yuan, Wei
Wang, Guanyang
Computation
Methodology
Machine Learning
In sampling tasks, it is common for target distributions to be known up to a normalizing constant. However, in many situations, even evaluating the unnormalized distribution can be costly or infeasible. This issue arises in scenarios such as sampling from the Bayesian posterior for tall datasets and the 'doubly-intractable' distributions. In this paper, we begin by observing that seemingly different Markov chain Monte Carlo (MCMC) algorithms, such as the exchange algorithm, PoissonMH, and TunaMH, can be unified under a simple common procedure. We then extend this procedure into a novel framework that allows the use of auxiliary variables in both the proposal and the acceptance-rejection step. Several new MCMC algorithms emerge from this framework that utilize estimated gradients to guide the proposal moves. They have demonstrated significantly better performance than existing methods on both synthetic and real datasets. Additionally, we develop the theory of the new framework and apply it to existing algorithms to simplify and extend their results.
title Markov chain Monte Carlo without evaluating the target: an auxiliary variable approach
topic Computation
Methodology
Machine Learning
url https://arxiv.org/abs/2406.05242