Parameter Optimization of Domain-Wall Fermion using Machine Learning

TL;DR

This paper applies machine learning to optimize parameters of domain-wall fermions, aiming to reduce chiral symmetry violation in lattice QCD simulations by treating certain coefficients as trainable parameters.

Contribution

It introduces a novel machine learning framework for parameter optimization in domain-wall fermions to enhance chiral symmetry preservation.

Findings

Feasibility demonstrated on a small lattice.

Residual mass can be effectively minimized.

Machine learning approach reduces chiral symmetry violation.

Abstract

We study a parameter optimization of domain-wall fermions to improve chiral symmetry based on machine learning. Domain-wall fermions involve coefficients along the fifth dimension, which can be treated as trainable parameters to reduce the chiral symmetry violation caused by the finite extent of the fifth dimension. As the loss function, we use the residual mass estimated stochastically on a single gauge configuration. Numerical tests on a $L^3\times T\times L_5=4^3\times8\times8$ lattice demonstrate the feasibility of this framework.