Machine learning action parameters in lattice quantum chromodynamics

TL;DR

This paper explores the use of deep neural networks to improve the efficiency of lattice quantum chromodynamics calculations by enabling better parameter regression, addressing computational challenges in particle physics research.

Contribution

It demonstrates that deep neural networks can effectively perform parametric regression in lattice QCD, outperforming traditional methods like principal component analysis.

Findings

Deep neural networks provide efficient parameter regression in lattice QCD.

Custom neural network layers are necessary to handle lattice QCD symmetries.

Machine learning can access computationally intractable regions of parameter space.

Abstract

Numerical lattice quantum chromodynamics studies of the strong interaction are important in many aspects of particle and nuclear physics. Such studies require significant computing resources to undertake. A number of proposed methods promise improved efficiency of lattice calculations, and access to regions of parameter space that are currently computationally intractable, via multi-scale action-matching approaches that necessitate parametric regression of generated lattice datasets. The applicability of machine learning to this regression task is investigated, with deep neural networks found to provide an efficient solution even in cases where approaches such as principal component analysis fail. The high information content and complex symmetries inherent in lattice QCD datasets require custom neural network layers to be introduced and present opportunities for further development.