Wasserstein Control of Mirror Langevin Monte Carlo

02/11/2020
by   Kelvin Shuangjian Zhang, et al.
0

Discretized Langevin diffusions are efficient Monte Carlo methods for sampling from high dimensional target densities that are log-Lipschitz-smooth and (strongly) log-concave. In particular, the Euclidean Langevin Monte Carlo sampling algorithm has received much attention lately, leading to a detailed understanding of its non-asymptotic convergence properties and of the role that smoothness and log-concavity play in the convergence rate. Distributions that do not possess these regularity properties can be addressed by considering a Riemannian Langevin diffusion with a metric capturing the local geometry of the log-density. However, the Monte Carlo algorithms derived from discretizations of such Riemannian Langevin diffusions are notoriously difficult to analyze. In this paper, we consider Langevin diffusions on a Hessian-type manifold and study a discretization that is closely related to the mirror-descent scheme. We establish for the first time a non-asymptotic upper-bound on the sampling error of the resulting Hessian Riemannian Langevin Monte Carlo algorithm. This bound is measured according to a Wasserstein distance induced by a Riemannian metric ground cost capturing the Hessian structure and closely related to a self-concordance-like condition. The upper-bound implies, for instance, that the iterates contract toward a Wasserstein ball around the target density whose radius is made explicit. Our theory recovers existing Euclidean results and can cope with a wide variety of Hessian metrics related to highly non-flat geometries.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/24/2018

On sampling from a log-concave density using kinetic Langevin diffusions

Langevin diffusion processes and their discretizations are often used fo...
research
06/20/2019

Bounding the error of discretized Langevin algorithms for non-strongly log-concave targets

In this paper, we provide non-asymptotic upper bounds on the error of sa...
research
02/15/2018

On the Theory of Variance Reduction for Stochastic Gradient Monte Carlo

We provide convergence guarantees in Wasserstein distance for a variety ...
research
02/16/2023

Improved Discretization Analysis for Underdamped Langevin Monte Carlo

Underdamped Langevin Monte Carlo (ULMC) is an algorithm used to sample f...
research
03/22/2023

Non-asymptotic analysis of Langevin-type Monte Carlo algorithms

We study Langevin-type algorithms for sampling from Gibbs distributions ...
research
02/24/2018

Dimensionally Tight Bounds for Second-Order Hamiltonian Monte Carlo

Hamiltonian Monte Carlo (HMC) is a widely deployed method to sample from...
research
05/31/2017

Bridge Simulation and Metric Estimation on Landmark Manifolds

We present an inference algorithm and connected Monte Carlo based estima...

Please sign up or login with your details

Forgot password? Click here to reset