Saved in:
Bibliographic Details
Main Authors: Aarts, Gert, Habibi, Diaa E., Ipp, Andreas, Müller, David I., Ranner, Thomas R., Wang, Lingxiao, Wang, Wei, Zhu, Qianteng
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.19552
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915757818904576
author Aarts, Gert
Habibi, Diaa E.
Ipp, Andreas
Müller, David I.
Ranner, Thomas R.
Wang, Lingxiao
Wang, Wei
Zhu, Qianteng
author_facet Aarts, Gert
Habibi, Diaa E.
Ipp, Andreas
Müller, David I.
Ranner, Thomas R.
Wang, Lingxiao
Wang, Wei
Zhu, Qianteng
contents We demonstrate that gauge equivariant diffusion models can accurately model the physics of non-Abelian lattice gauge theory using the Metropolis-adjusted annealed Langevin algorithm (MAALA), as exemplified by computations in two-dimensional U(2) and SU(2) gauge theories. Our network architecture is based on lattice gauge equivariant convolutional neural networks (L-CNNs), which respect local and global symmetries on the lattice. Models are trained on a single ensemble generated using a traditional Monte Carlo method. By studying Wilson loops of various size as well as the topological susceptibility, we find that the diffusion approach generalizes remarkably well to larger inverse couplings and lattice sizes with negligible loss of accuracy while retaining moderately high acceptance rates.
format Preprint
id arxiv_https___arxiv_org_abs_2601_19552
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Generalizable Equivariant Diffusion Models for Non-Abelian Lattice Gauge Theory
Aarts, Gert
Habibi, Diaa E.
Ipp, Andreas
Müller, David I.
Ranner, Thomas R.
Wang, Lingxiao
Wang, Wei
Zhu, Qianteng
High Energy Physics - Lattice
Machine Learning
We demonstrate that gauge equivariant diffusion models can accurately model the physics of non-Abelian lattice gauge theory using the Metropolis-adjusted annealed Langevin algorithm (MAALA), as exemplified by computations in two-dimensional U(2) and SU(2) gauge theories. Our network architecture is based on lattice gauge equivariant convolutional neural networks (L-CNNs), which respect local and global symmetries on the lattice. Models are trained on a single ensemble generated using a traditional Monte Carlo method. By studying Wilson loops of various size as well as the topological susceptibility, we find that the diffusion approach generalizes remarkably well to larger inverse couplings and lattice sizes with negligible loss of accuracy while retaining moderately high acceptance rates.
title Generalizable Equivariant Diffusion Models for Non-Abelian Lattice Gauge Theory
topic High Energy Physics - Lattice
Machine Learning
url https://arxiv.org/abs/2601.19552