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

Abstract

Sampling is a fundamental and arguably very important task with numerous applications in Machine Learning. One approach to sample from a high dimensional distribution $e^{-f}$ for some function $f$ is the Langevin Algorithm (LA). Recently, there has been a lot of progress in showing fast convergence of LA even in cases where $f$ is non-convex, notably [53], [39] in which the former paper focuses on functions $f$ defined in ${\mathbb{R}}^n$ and the latter paper focuses on functions with symmetries (like matrix completion type objectives) with manifold structure. Our work generalizes the results of [53] where $f$ is defined on a manifold $M$ rather than ${\mathbb{R}}^n$. From technical point of view, we show that KL decreases in a geometric rate whenever the distribution $e^{-f}$ satisfies a log-Sobolev inequality on $M$.

References in corpus (16)

• User-friendly guarantees for the Langevin Monte Carlo with inaccurate gradient
• Non-asymptotic convergence analysis for the Unadjusted Langevin Algorithm
• Convergence of Langevin MCMC in KL-divergence
• Measuring Sample Quality with Kernels
• On the convergence of Hamiltonian Monte Carlo
• Is There an Analog of Nesterov Acceleration for MCMC?
• Rapid Convergence of the Unadjusted Langevin Algorithm: Isoperimetry Suffices
• Dimensionally Tight Bounds for Second-Order Hamiltonian Monte Carlo
• Langevin Monte Carlo and JKO splitting
• Analysis of Langevin Monte Carlo via convex optimization
• Proximal Langevin Algorithm: Rapid Convergence Under Isoperimetry
• Couplings and quantitative contraction rates for Langevin dynamics
• Wasserstein Control of Mirror Langevin Monte Carlo
• Langevin Monte Carlo without smoothness
• Fast Convergence for Langevin Diffusion with Manifold Structure
• Stochastic natural gradient descent draws posterior samples in function space

Cited by in corpus (1)

• Spherical Sliced-Wasserstein