Machine learning improves calculations in lattice quantum field theory
Machine learning for lattice QCD
Machine Learning
Summary
Simulating fundamental particles and forces on a grid is very computationally intensive. The authors review how machine learning is being used to speed up these lattice field theory calculations without losing accuracy. They focus on well-established methods as of 2025, marking 50 years since the start of lattice gauge theory studies. This helps researchers get more precise results faster.
What this means in practice
- •For computational physicists: Optimize large-scale lattice QCD calculations by integrating established ML methods to reduce computation time without uncontrolled approximations.
- •For data scientists in physics labs: Implement ML techniques validated in lattice field theory to improve simulation accuracy and efficiency in complex physical models.
A survey. It maps existing work.
Authors
Gurtej Kanwar, Scott Lawrence, Alessandro Nada, Phiala Shanahan
Abstract
Machine learning (ML) methods have been explored as a means of optimizing lattice field theory calculations, with increasing interest in recent years. This chapter gives an introduction and summary to the use of ML methods to optimize lattice field theory without introducing any uncontrolled approximations. We focus on those directions which are clearly established as of late 2025, marking the 50th anniversary of the beginning of the study of lattice gauge theory. This chapter is a contribution to the online book ``Lattice QCD at 50 years,'' (LQCD@50), edited by Tanmoy Bhattacharya, Maarten Golterman, Rajan Gupta, Laurent Lellouch, and Steve Sharpe.