Generalizable equivariant diffusion models for non-Abelian lattice gauge theory
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.
Authors
- Andreas Ipp (ORCID: https://orcid.org/0000-0001-9511-3523)
- David I. Müller (ORCID: https://orcid.org/0000-0002-8163-7614)
- Gert Aarts A (ORCID: https://orcid.org/0000-0002-6038-3782)
- Qianteng Zhu (ORCID: https://orcid.org/0009-0001-1405-2683)
- Diaa Eddin Habibi (ORCID: https://orcid.org/0009-0004-4942-1516)
- Wei Wang (ORCID: https://orcid.org/0009-0004-7194-2465)
- Lingxiao Wang
- Thomas R. Ranner
Publication Details
- Journal
- Physical Review Letters
- Published
- 2026-11-16
- DOI
- https://doi.org/10.1103/lhpb-v7q7
- Citations
- 31
- Primary Topic
- Quantum Chromodynamics and Particle Interactions
- Type
- article
- Field-Weighted Citation Impact
- 20.11
Funders
- UK Research and Innovation
- Leverhulme Trust
- National Natural Science Foundation of China
- Austrian Science Fund
- Science and Technology Facilities Council
- Japan Society for the Promotion of Science
- RIKEN