Fast Convergence of $\Phi$-Divergence Along the Unadjusted Langevin Algorithm and Proximal Sampler

TL;DR

This paper proves that the Unadjusted Langevin Algorithm and Proximal Sampler exhibit exponential convergence in various $\

Contribution

It extends mixing time analysis to $\\Phi$-divergence for these algorithms, showing exponential decay under $\\Phi$-Sobolev inequalities, broadening understanding of their convergence properties.

Findings

Exponential convergence in $\\Phi$-divergence for Langevin-based algorithms.

Includes special cases like chi-squared and relative entropy mixing regimes.

Convergence analysis via noisy channel interpretation and strong data processing inequalities.

Abstract

We study the mixing time of two popular discrete-time Markov chains in continuous space, the Unadjusted Langevin Algorithm and the Proximal Sampler, which are discretizations of the Langevin dynamics. We extend mixing time analyses for these Markov chains to hold in $\Phi$-divergence. We show that any $\Phi$-divergence arising from a twice-differentiable strictly convex function $\Phi$ converges to $0$ exponentially fast along these Markov chains, under the assumption that their stationary distributions satisfy the corresponding $\Phi$-Sobolev inequality, which holds for example when the target distribution of the Langevin dynamics is strongly log-concave. Our setting includes as special cases popular mixing time regimes, namely the mixing in chi-squared divergence under a Poincar\'e inequality, and the mixing in relative entropy under a log-Sobolev inequality. Our results follow by viewing the sampling algorithms as noisy channels and bounding the contraction coefficients arising in the appropriate strong data processing inequalities.