Speaker
Sam Foreman
(Argonne National Laboratory)
Description
We propose using Normalizing Flows as a trainable kernel within the molecular dynamics update of Hamiltonian Monte Carlo (HMC). By learning (invertible) transformations that simplify our dynamics, we can outperform traditional methods at generating independent configurations. We show that, using a carefully constructed network architecture, our approach can be easily scaled to large lattice volumes with minimal retraining effort.
Primary authors
Sam Foreman
(Argonne National Laboratory)
Luchang Jin
Xiao-Yong Jin
(Argonne National Laboratory)
Akio Tomiya
(RIKEN BNL Research Center)
James C Osborn
(Argonne ALCF)
Taku Izubuchi
(Brookhaven National Laboratory)
