Generative models for lattice quantum field theory

Phiala Shanahan
Massachusetts Institute of Technology

I will discuss opportunities for machine learning, in particular generative models, to accelerate lattice quantum field theory calculations of key nuclear physics processes from the Standard Model of particle physics. Particular challenges in this context include incorporating complex (gauge) symmetries into model architectures, and scaling models to the large number of degrees of freedom of state-of-the-art numerical studies.

Presentation (PDF File)

Back to Workshop I: From Passive to Active: Generative and Reinforcement Learning with Physics