Machine learning mapping of lattice correlated data

Author:

Jangho Kim, Giovanni Pederiva, Andrea Shindler

Keyword:

High Energy Physics - Lattice, High Energy Physics - Lattice (hep-lat)

journal:

date:

2024-02-12 00:00:00

Abstract

We discuss a novel approach based on machine learning (ML) regression models to reduce the computational cost of disconnected diagrams in lattice QCD calculations. This method creates a mapping between the results of fermionic loops computed at different quark masses and flow times. The ML model, trained with just a small fraction of the complete data set, provides similar predictions and uncertainties over the calculation done over the whole ensemble, resulting in a significant computational gain.

PDF: Machine learning mapping of lattice correlated data.pdf