Equivariant flow-based sampling for lattice gauge theory

Sebastien Racaniere, Danilo Jimenez Rezende, Gurtej Kanwar, Phiala Shanahan, Kyle Cranmer, Michael Samuel Albergo, Denis Boyda, Daniel Hackett

Abstract: We define a class of machine-learned flow-based sampling algorithms for lattice gauge theories that are gauge invariant by construction. We demonstrate the application of this framework to U (1) gauge theory in two spacetime dimensions, and find that, at small bare coupling, the approach is orders of magnitude more efficient at sampling topological quantities than more traditional sampling procedures such as hybrid Monte Carlo and heat bath.