Lecture

Convergence of Langevin Monte Carlo: Tail Growth and Smoothness

Description

This lecture by the instructor explores the convergence properties of Langevin Monte Carlo (LMC) algorithms, focusing on the interplay between tail growth and smoothness of the target distribution. The lecture covers topics such as the sampling from Gibbs measures, the transition from discrete algorithms to continuous diffusion, and the convergence analysis of LMC under different growth rates. It also delves into the theoretical guarantees for LMC, the role of degenerately convex potentials, and the modified Log-Sobolev inequality. The main theorem presented in the lecture establishes the conditions under which LMC achieves fast convergence rates for a wide class of potentials, including non-convex and non-smooth functions.

About this result
This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.