Rapid Convergence of the Unadjusted Langevin Algorithm: Log-Sobolev Suffices

03/20/2019

∙

We prove a convergence guarantee on the unadjusted Langevin algorithm for sampling assuming only that the target distribution e^-f satisfies a log-Sobolev inequality and the Hessian of f is bounded. In particular, f is not required to be convex or have higher derivatives bounded.

READ FULL TEXT

Rapid Convergence of the Unadjusted Langevin Algorithm: Log-Sobolev Suffices

Proximal Langevin Algorithm: Rapid Convergence Under Isoperimetry

Fast Convergence of Langevin Dynamics on Manifold: Geodesics meet Log-Sobolev

Convergence in KL Divergence of the Inexact Langevin Algorithm with Application to Score-based Generative Models

Convergence of Dümbgen's Algorithm for Estimation of Tail Inflation

Analysis of Langevin Monte Carlo from Poincaré to Log-Sobolev

Mirrored Langevin Dynamics

Finite Precision Stochastic Optimisation -- Accounting for the Bias

Rapid Convergence of the Unadjusted Langevin Algorithm: Log-Sobolev Suffices

Related Research

Proximal Langevin Algorithm: Rapid Convergence Under Isoperimetry

Fast Convergence of Langevin Dynamics on Manifold: Geodesics meet Log-Sobolev

Convergence in KL Divergence of the Inexact Langevin Algorithm with Application to Score-based Generative Models

Convergence of Dümbgen's Algorithm for Estimation of Tail Inflation

Analysis of Langevin Monte Carlo from Poincaré to Log-Sobolev

Mirrored Langevin Dynamics

Finite Precision Stochastic Optimisation -- Accounting for the Bias