Multivariate Stein factors for a class of strongly log-concave distributions

DOI10.1214/16-ECP15MaRDI QIDQ321144zbMATH OpenOpenAlexWikidataFDO

Authors Lester Mackey, Jackson Gorham

Publication date 7 October 2016

Published in Electronic Communications in Probability (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1512.07392, https://projecteuclid.org/euclid.ecp/1472830238

zbMATH Keywords

Stein's methodgenerator methodmultivariate log-concave distributionoverdamped Langevin diffusionStein discrepancyStein factorssynchronous coupling

Mathematics Subject Classification ID

Inequalities; stochastic orderings (60E15) Diffusion processes (60J60) Approximations to statistical distributions (nonasymptotic) (62E17)

Abstract: We establish uniform bounds on the low-order derivatives of Stein equation solutions for a broad class of multivariate, strongly log-concave target distributions. These "Stein factor" bounds deliver control over Wasserstein and related smooth function distances and are well-suited to analyzing the computable Stein discrepancy measures of Gorham and Mackey. Our arguments of proof are probabilistic and feature the synchronous coupling of multiple overdamped Langevin diffusions.

Recommendations

• Erratum: ``Multivariate Stein factors for a class of strongly log-concave distributions
• Measuring sample quality with diffusions
• On the optimality of Stein factors
• Multivariate approximations in Wasserstein distance by Stein's method and Bismut's formula
• Stein's density method for multivariate continuous distributions

Cited in

(13)

• On Stein's method for multivariate self-decomposable laws with finite first moment
• Measuring sample quality with diffusions
• A MULTIVARIATE VERSION OF STEIN'S IDENTITY WITH APPLICATIONS TO MOMENT CALCULATIONS AND ESTIMATION OF CONDITIONALLY SPECIFIED DISTRIBUTIONS
• Weighted Poincaré inequalities, concentration inequalities and tail bounds related to Stein kernels in dimension one
• Multivariate approximations in Wasserstein distance by Stein's method and Bismut's formula
• Erratum: ``Multivariate Stein factors for a class of strongly log-concave distributions
• Stein factors for variance-gamma approximation in the Wasserstein and Kolmogorov distances
• The prelimit generator comparison approach of Stein's method
• A diffusion approach to Stein's method on Riemannian manifolds
• On the optimality of Stein factors
• Stein's method meets computational statistics: a review of some recent developments
• First-order covariance inequalities via Stein's method
• Stein's density method for multivariate continuous distributions

This page was built for publication: Multivariate Stein factors for a class of strongly log-concave distributions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q321144)