Timezone: »

Fast Convergence of Langevin Dynamics on Manifold: Geodesics meet Log-Sobolev
Xiao Wang · Qi Lei · Ioannis Panageas

Thu Dec 10 09:00 AM -- 11:00 AM (PST) @ Poster Session 5 #1629
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 \cite{VW19}, \cite{MoritaRisteski} 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 \cite{VW19} 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 $M$.

Author Information

Xiao Wang (Singapore university of technology and design)
Qi Lei (Princeton University)
Ioannis Panageas (UC Irvine)

More from the Same Authors