The Langevin Monte Carlo algorithm in the non-smooth log-concave case

DOI10.1214/23-AAP1935MaRDI QIDQ6138925zbMATH OpenFDO

Authors Joseph Lehec

Publication date 16 January 2024

Published in The Annals of Applied Probability (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2101.10695

zbMATH Keywords

Markov chain Monte Carloconvexitystatistical sampling

Mathematics Subject Classification ID

Monte Carlo methods (65C05) Sampling theory, sample surveys (62D05) Randomized algorithms (68W20) Asymptotic theory of convex bodies (52A23)

Abstract: We prove non asymptotic polynomial bounds on the convergence of the Langevin Monte Carlo algorithm in the case where the potential is a convex function which is globally Lipschitz on its domain, typically the maximum of a finite number of affine functions on an arbitrary convex set. In particular the potential is not assumed to be gradient Lipschitz, in contrast with most existing works on the topic.

Cites work

• scientific article; zbMATH DE number 3780265 (Why is no real title available?)
• scientific article; zbMATH DE number 1515832 (Why is no real title available?)
• scientific article; zbMATH DE number 816099 (Why is no real title available?)
• A note on quadratic transportation and divergence inequality
• A random polynomial-time algorithm for approximating the volume of convex bodies
• An almost constant lower bound of the isoperimetric coefficient in the KLS conjecture
• Analysis and geometry of Markov diffusion operators
• Bourgain's slicing problem and KLS isoperimetry up to polylog
• Convex measures on locally convex spaces
• From Brunn-Minkowski to Brascamp-Lieb and to logarithmic Sobolev inequalities
• From concentration to isoperimetry: semigroup proofs
• Generalization of an inequality by Talagrand and links with the logarithmic Sobolev inequality
• High-dimensional Bayesian inference via the unadjusted Langevin algorithm
• Hypercontractivity of Hamilton-Jacobi equations.
• Isoperimetric and concentration inequalities: equivalence under curvature lower bound
• Isoperimetric problems for convex bodies and a localization lemma
• Sampling from a log-concave distribution with projected Langevin Monte Carlo
• Sections of convex bodies through their centroid
• Stochastic differential equations with reflecting boundary condition in convex regions
• The Poincaré inequality and quadratic transportation-variance inequalities
• Theoretical Guarantees for Approximate Sampling from Smooth and Log-Concave Densities
• Thin shell implies spectral gap up to polylog via a stochastic localization scheme

Cited in

(1)

• NF-ULA: normalizing flow-based unadjusted Langevin algorithm for imaging inverse problems

This page was built for publication: The Langevin Monte Carlo algorithm in the non-smooth log-concave case

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6138925)