Transferable Implicit Transfer Operators

Abstract: In this talk, I will outline our approach to use deep generative models to learn weak solutions to the Langevin equations with long time horizons. E.g. given an initial condition, $x_0$, learn the transition density $p_t(x_t\mid x_0)$, where $t$ is orders of magnitude larger than the usual numerical integration step. The context of this work is the $\textit{sampling problem}$ from molecular dynamics, an important method in chemistry, physics, and biology, that faces slow mixing. I will give numerous empirical examples of the successful application of this approach in molecular dynamics.

machine learningprobabilitystatistics theory

Audience: researchers in the discipline

Gothenburg statistics seminar

Series comments: Gothenburg statistics seminar is open to the interested public, everybody is welcome. It usually takes place in MVL14 (http://maps.chalmers.se/#05137ad7-4d34-45e2-9d14-7f970517e2b60, see specific talk). Speakers are asked to prepare material for 35 minutes excluding questions from the audience.