Machine-learned RG-improved gauge actions and classically perfect gradient flows

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Holland, Kieran, Ipp, Andreas, Müller, David I., Wenger, Urs
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912901108858880
author Holland, Kieran
Ipp, Andreas
Müller, David I.
Wenger, Urs
author_facet Holland, Kieran
Ipp, Andreas
Müller, David I.
Wenger, Urs
contents Extracting continuum properties of quantum field theories from discretized spacetime is challenging due to lattice artifacts. Renormalization-group (RG)-improved lattice actions can preserve continuum properties, but are in general difficult to parameterize. Machine learning (ML) with gauge-equivariant convolutional neural networks provides a way to efficiently describe such actions. We test a machine-learned RG-improved lattice gauge action, the classically perfect fixed-point (FP) action, for four-dimensional SU(3) gauge theory through Monte Carlo simulations. We establish that the gradient flow of the FP action is free of tree-level discretization effects to all orders in the lattice spacing, making it classically perfect. This allows us to test the quality of improvement of the FP action, without introducing additional artifacts. We find that discretization effects in gradient-flow observables are highly suppressed and less than 1% up to lattice spacings of 0.14 fm, allowing continuum physics to be extracted from coarse lattices. The quality of improvement achieved motivates the use of the FP action in future gauge theory studies. The advantages of ML-based parameterizations also highlight the possibility of realizing quantum perfect actions in lattice gauge theory.
format Preprint
id arxiv_https___arxiv_org_abs_2504_15870
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Machine-learned RG-improved gauge actions and classically perfect gradient flows
Holland, Kieran
Ipp, Andreas
Müller, David I.
Wenger, Urs
High Energy Physics - Lattice
Extracting continuum properties of quantum field theories from discretized spacetime is challenging due to lattice artifacts. Renormalization-group (RG)-improved lattice actions can preserve continuum properties, but are in general difficult to parameterize. Machine learning (ML) with gauge-equivariant convolutional neural networks provides a way to efficiently describe such actions. We test a machine-learned RG-improved lattice gauge action, the classically perfect fixed-point (FP) action, for four-dimensional SU(3) gauge theory through Monte Carlo simulations. We establish that the gradient flow of the FP action is free of tree-level discretization effects to all orders in the lattice spacing, making it classically perfect. This allows us to test the quality of improvement of the FP action, without introducing additional artifacts. We find that discretization effects in gradient-flow observables are highly suppressed and less than 1% up to lattice spacings of 0.14 fm, allowing continuum physics to be extracted from coarse lattices. The quality of improvement achieved motivates the use of the FP action in future gauge theory studies. The advantages of ML-based parameterizations also highlight the possibility of realizing quantum perfect actions in lattice gauge theory.
title Machine-learned RG-improved gauge actions and classically perfect gradient flows
topic High Energy Physics - Lattice
url https://arxiv.org/abs/2504.15870