Exponential ergodicity of mirror-Langevin diffusions
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.