Quantitative spectral gap estimate and Wasserstein contraction of simple slice sampling

DOI10.1214/20-AAP1605MaRDI QIDQ6315334arXivFDO

Authors Viacheslav Natarovskii, Daniel Rudolf, Björn Sprungk

Publication date 9 March 2019

Published in arXiv

Full work available at URL https://doi.org/10.1214/20-AAP1605

Mathematics Subject Classification ID

Computational methods in Markov chains (60J22) Statistical sampling theory and related topics (62D99) Monte Carlo methods (65C05) Numerical analysis or methods applied to Markov chains (65C40)

arXiv classification

math.PRmath.STstat.TH

Abstract: We prove Wasserstein contraction of simple slice sampling for approximate sampling w.r.t. distributions with log-concave and rotational invariant Lebesgue densities. This yields, in particular, an explicit quantitative lower bound of the spectral gap of simple slice sampling. Moreover, this lower bound carries over to more general target distributions depending only on the volume of the (super-)level sets of their unnormalized density.

This page was built for publication: Quantitative spectral gap estimate and Wasserstein contraction of simple slice sampling

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6315334)