Wasserstein contraction and spectral gap of slice sampling revisited

DOI10.1214/23-EJP1030arXiv2305.16984OpenAlexW4388411989MaRDI QIDQ6136814FDOQ6136814

Authors: Philip Schär 

Publication date: 17 January 2024

Published in: Electronic Journal of Probability (Search for Journal in Brave)

Abstract: We propose a new class of Markov chain Monte Carlo methods, called $k$-polar slice sampling ($k$-PSS), as a technical tool that interpolates between and extrapolates beyond uniform and polar slice sampling. By examining Wasserstein contraction rates and spectral gaps of $k$-PSS, we obtain strong quantitative results regarding its performance for different kinds of target distributions. Because $k$-PSS contains uniform and polar slice sampling as special cases, our results significantly advance the theoretical understanding of both of these methods. In particular, we prove realistic estimates of the convergence rates of uniform slice sampling for arbitrary multivariate Gaussian distributions on the one hand, and near-arbitrary multivariate t-distributions on the other. Furthermore, our results suggest that for heavy-tailed distributions, polar slice sampling performs dimension-independently well, whereas uniform slice sampling suffers a rather strong curse of dimensionality.

Full work available at URL: https://arxiv.org/abs/2305.16984

Recommendations

• Dimension-independent spectral gap of polar slice sampling
• The polar slice sampler
• Efficiency and Convergence Properties of Slice Samplers
• Slice sampling. (With discussions and rejoinder)

zbMATH Keywords

slice samplingMCMCspectral gapWasserstein contraction

Mathematics Subject Classification ID

Computational methods in Markov chains (60J22) Monte Carlo methods (65C05) Discrete-time Markov processes on general state spaces (60J05)

Cites Work

• Slice sampling. (With discussions and rejoinder)
• Title not available (Why is that?)
• Central limit theorem for additive functionals of reversible Markov processes and applications to simple exclusions
• Batch means and spectral variance estimators in Markov chain Monte Carlo
• Title not available (Why is that?)
• Ricci curvature of Markov chains on metric spaces
• Measures, Integrals and Martingales
• Markov Chains
• The polar slice sampler
• Convergence of Slice Sampler Markov Chains
• Explicit error bounds for Markov chain Monte Carlo
• Computation of expectations by Markov chain Monte Carlo methods
• Quantitative spectral gap estimate and Wasserstein contraction of simple slice sampling

Cited In (2)

• Dimension-independent spectral gap of polar slice sampling
• A dimension-independent bound on the Wasserstein contraction rate of a geodesic random walk on the sphere

This page was built for publication: Wasserstein contraction and spectral gap of slice sampling revisited

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6136814)