Saved in:
Bibliographic Details
Main Authors: Li, Zeyu, Zhu, Guorui, He, Wenjie, Feng, Bo, Chen, Jiaqi, Luo, Ming-xing, Yang, Gang
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.24494
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911236789108736
author Li, Zeyu
Zhu, Guorui
He, Wenjie
Feng, Bo
Chen, Jiaqi
Luo, Ming-xing
Yang, Gang
author_facet Li, Zeyu
Zhu, Guorui
He, Wenjie
Feng, Bo
Chen, Jiaqi
Luo, Ming-xing
Yang, Gang
contents We employ the Transformer to learn patterns in two-dimensional lattice Yang-Mills theory. Specifically, we represent both Wilson loops and their expectation values as tokenized sequences. Taking the shape of Wilson loops as input, the model successfully predicts expectation values with high accuracy, indicating a meaningful connection between loop geometry and physical results. Our study differs from prior machine learning applications in lattice QCD by emphasizing analytical structures rather than numerical computations. We explore model performance under varying hyperparameters, training data sizes, and sequence lengths. This work serves as a first step toward extending such methods to higher dimensions and inspiring rigorous analytical derivations.
format Preprint
id arxiv_https___arxiv_org_abs_2510_24494
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AI for Pattern Hunter: Application in Wilson Loop of 2D Lattice Yang-Mills Theory
Li, Zeyu
Zhu, Guorui
He, Wenjie
Feng, Bo
Chen, Jiaqi
Luo, Ming-xing
Yang, Gang
High Energy Physics - Theory
We employ the Transformer to learn patterns in two-dimensional lattice Yang-Mills theory. Specifically, we represent both Wilson loops and their expectation values as tokenized sequences. Taking the shape of Wilson loops as input, the model successfully predicts expectation values with high accuracy, indicating a meaningful connection between loop geometry and physical results. Our study differs from prior machine learning applications in lattice QCD by emphasizing analytical structures rather than numerical computations. We explore model performance under varying hyperparameters, training data sizes, and sequence lengths. This work serves as a first step toward extending such methods to higher dimensions and inspiring rigorous analytical derivations.
title AI for Pattern Hunter: Application in Wilson Loop of 2D Lattice Yang-Mills Theory
topic High Energy Physics - Theory
url https://arxiv.org/abs/2510.24494