Machine Learning Estimators for Lattice QCD Observables

TL;DR

This paper introduces a machine learning approach to efficiently estimate lattice QCD observables, significantly reducing computational costs while maintaining accuracy across different calculations.

Contribution

The authors develop a novel ML-based method that predicts QCD observables from less expensive data, demonstrating cost reductions of up to 38% with bias estimation techniques.

Findings

Achieved 7-38% reduction in computational cost.

Successfully predicted nucleon three-point functions and neutron mass phase.

Validated bias estimation method for ML predictions.

Abstract

A novel technique using machine learning (ML) to reduce the computational cost of evaluating lattice quantum chromodynamics (QCD) observables is presented. The ML is trained on a subset of background gauge field configurations, called the labeled set, to predict an observable $O$ from the values of correlated, but less compute-intensive, observables $\mathbf{X}$ calculated on the full sample. By using a second subset, also part of the labeled set, we estimate the bias in the result predicted by the trained ML algorithm. A reduction in the computational cost by about $7\%-38\%$ is demonstrated for two different lattice QCD calculations using the Boosted decision tree regression ML algorithm: (1) prediction of the nucleon three-point correlation functions that yield isovector charges from the two-point correlation functions, and (2) prediction of the phase acquired by the neutron mass when a small Charge-Parity (CP) violating interaction, the quark chromoelectric dipole moment interaction, is added to QCD, again from the two-point correlation functions calculated without CP violation.