Monday, November 30, 1:00 p.m.
Gurtej Kanwar - MIT
Ensemble generation for lattice QFT using machine learning
Abstract - Monte Carlo sampling is a powerful method to compute observables in quantum field theories regularized on a discrete spacetime lattice (LQFT), which is necessary for example to study the non-perturbative behavior of QCD in the low-energy regime. The cost of drawing independent samples is a major bottleneck in such studies. I discuss our recent work demonstrating that generative machine-learning models can be used to perform Monte Carlo sampling and produce unbiased estimates of observables in LQFT. This work lays out a framework for exactly encoding translational and gauge symmetries in these models, making training practically viable.