Stereographic Markov Chain Monte Carlo

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Jun, Łatuszyński, Krzysztof, Roberts, Gareth O.
Format: Preprint
Published: 2022
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911780735811584
author Yang, Jun
Łatuszyński, Krzysztof
Roberts, Gareth O.
author_facet Yang, Jun
Łatuszyński, Krzysztof
Roberts, Gareth O.
contents High-dimensional distributions, especially those with heavy tails, are notoriously difficult for off-the-shelf MCMC samplers: the combination of unbounded state spaces, diminishing gradient information, and local moves results in empirically observed ``stickiness'' and poor theoretical mixing properties -- lack of geometric ergodicity. In this paper, we introduce a new class of MCMC samplers that map the original high-dimensional problem in Euclidean space onto a sphere and remedy these notorious mixing problems. In particular, we develop random-walk Metropolis type algorithms as well as versions of the Bouncy Particle Sampler that are uniformly ergodic for a large class of light and heavy-tailed distributions and also empirically exhibit rapid convergence in high dimensions. In the best scenario, the proposed samplers can enjoy the ``blessings of dimensionality'' that the convergence is faster in higher dimensions.
format Preprint
id arxiv_https___arxiv_org_abs_2205_12112
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Stereographic Markov Chain Monte Carlo
Yang, Jun
Łatuszyński, Krzysztof
Roberts, Gareth O.
Computation
Methodology
Machine Learning
High-dimensional distributions, especially those with heavy tails, are notoriously difficult for off-the-shelf MCMC samplers: the combination of unbounded state spaces, diminishing gradient information, and local moves results in empirically observed ``stickiness'' and poor theoretical mixing properties -- lack of geometric ergodicity. In this paper, we introduce a new class of MCMC samplers that map the original high-dimensional problem in Euclidean space onto a sphere and remedy these notorious mixing problems. In particular, we develop random-walk Metropolis type algorithms as well as versions of the Bouncy Particle Sampler that are uniformly ergodic for a large class of light and heavy-tailed distributions and also empirically exhibit rapid convergence in high dimensions. In the best scenario, the proposed samplers can enjoy the ``blessings of dimensionality'' that the convergence is faster in higher dimensions.
title Stereographic Markov Chain Monte Carlo
topic Computation
Methodology
Machine Learning
url https://arxiv.org/abs/2205.12112