Applications of Machine Learning to Lattice Quantum Field Theory

Abstract

There is great potential to apply machine learning in the area of numerical lattice quantum field theory, but full exploitation of that potential will require new strategies. In this white paper for the Snowmass community planning process, we discuss the unique requirements of machine learning for lattice quantum field theory research and outline what is needed to enable exploration and deployment of this approach in the future.

Prospects for precise predictions of $a_μ$ in the Standard Model

“…Further methodological developments, for example, to more efficiently generate gauge field ensembles with small lattice spacings and large volumes (see, for example, Refs. [225][226][227][228][229]) as well as improved statistical noise reduction (see, for example, Refs. [230][231][232]) would further enhance the impact of these future computational resources on the precision of the lattice QCD results.…”

A lattice QCD perspective on weak decays of b and c quarks Snowmass 2022 White Paper

“…With further improved numerical performance, fully dynamical simulations with up/down, strange, charm, and bottom quarks become possible [15], although a practical improvement due to simulating dynamical bottom quarks is most likely marginal. In addition machine learning techniques may offer new possibilities for LFT [16]. Complementary to LFT calculations would be to directly perform quantum simulations [17].…”

GomalizingFlow.jl: A Julia package for Flow-based sampling algorithm for lattice field theory

“…Machine learning algorithms to generate configurations for lattice field theory are widely investigated [13]. First trial has been done with the Boltzmann machine [14], and others like GAN [15,16] has been tried.…”