On the cost of Bayesian posterior mean strategy for log-concave models

Abstract

In this paper, we investigate the problem of computing Bayesian estimators using Langevin Monte-Carlo type approximation. The novelty of this paper is to consider together the statistical and numerical counterparts (in a general log-concave setting). More precisely, we address the following question: given $n$ observations in ${\mathbb{R}}^q$ distributed under an unknown probability ${\mathbb{P}}_{{\theta }^{\star }}$ with ${\theta }^{\star }\in {\mathbb{R}}^d$ , what is the optimal numerical strategy and its cost for the approximation of ${\theta }^{\star }$ with the Bayesian posterior mean? To answer this question, we establish some quantitative statistical bounds related to the underlying Poincaré constant of the model and establish new results about the numerical approximation of Gibbs measures by Cesaro averages of Euler schemes of (over-damped) Langevin diffusions. These last results include in particular some quantitative controls in the weakly convex case based on new bounds on the solution of the related Poisson equation of the diffusion.

References in corpus (6)

• Rates of contraction of posterior distributions based on Gaussian process priors
• Needles and Straw in a Haystack: Posterior concentration for possibly sparse sequences
• Sampling Can Be Faster Than Optimization
• Log-concave sampling: Metropolis-Hastings algorithms are fast
• Is There an Analog of Nesterov Acceleration for MCMC?
• Bounding the error of discretized Langevin algorithms for non-strongly log-concave targets