STLGMay 19, 2020

Exponential ergodicity of mirror-Langevin diffusions

arXiv:2005.09669v257 citations
Originality Highly original
AI Analysis

This addresses the problem of efficient sampling for computational statistics and optimization, though it builds directly on prior work (Zhang et al., 2020).

The paper analyzes mirror-Langevin diffusions for sampling from ill-conditioned log-concave distributions, proving that Newton-Langevin diffusions achieve exponential convergence with dimension-free rates independent of the target distribution.

Motivated by the problem of sampling from ill-conditioned log-concave distributions, we give a clean non-asymptotic convergence analysis of mirror-Langevin diffusions as introduced in Zhang et al. (2020). As a special case of this framework, we propose a class of diffusions called Newton-Langevin diffusions and prove that they converge to stationarity exponentially fast with a rate which not only is dimension-free, but also has no dependence on the target distribution. We give an application of this result to the problem of sampling from the uniform distribution on a convex body using a strategy inspired by interior-point methods. Our general approach follows the recent trend of linking sampling and optimization and highlights the role of the chi-squared divergence. In particular, it yields new results on the convergence of the vanilla Langevin diffusion in Wasserstein distance.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes