Proximal Langevin Sampling With Inexact Proximal Mapping

TL;DR

This paper analyzes a proximal Langevin sampling algorithm that accounts for errors in proximal operator evaluations, providing convergence guarantees and practical validation in Bayesian imaging inverse problems.

Contribution

It extends existing Langevin sampling theory to inexact proximal computations, quantifying bias and convergence under approximation errors.

Findings

Bias remains bounded with bounded errors

Bias converges to zero with decaying errors in strongly convex cases

Numerical experiments validate theoretical convergence results

Abstract

In order to solve tasks like uncertainty quantification or hypothesis tests in Bayesian imaging inverse problems, we often have to draw samples from the arising posterior distribution. For the usually log-concave but high-dimensional posteriors, Markov chain Monte Carlo methods based on time discretizations of Langevin diffusion are a popular tool. If the potential defining the distribution is non-smooth, these discretizations are usually of an implicit form leading to Langevin sampling algorithms that require the evaluation of proximal operators. For some of the potentials relevant in imaging problems this is only possible approximately using an iterative scheme. We investigate the behaviour of a proximal Langevin algorithm under the presence of errors in the evaluation of proximal mappings. We generalize existing non-asymptotic and asymptotic convergence results of the exact algorithm to our inexact setting and quantify the bias between the target and the algorithm's stationary distribution due to the errors. We show that the additional bias stays bounded for bounded errors and converges to zero for decaying errors in a strongly convex setting. We apply the inexact algorithm to sample numerically from the posterior of typical imaging inverse problems in which we can only approximate the proximal operator by an iterative scheme and validate our theoretical convergence results.