Saved in:
Bibliographic Details
Main Authors: Lal, Shailesh, Majumder, Suvajit, Sobko, Evgeny
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.10469
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916653324828672
author Lal, Shailesh
Majumder, Suvajit
Sobko, Evgeny
author_facet Lal, Shailesh
Majumder, Suvajit
Sobko, Evgeny
contents We introduce a novel machine learning based framework for discovering integrable models. Our approach first employs a synchronized ensemble of neural networks to find high-precision numerical solution to the Yang-Baxter equation within a specified class. Then, using an auxiliary system of algebraic equations, [Q_2, Q_3] = 0, and the numerical value of the Hamiltonian obtained via deep learning as a seed, we reconstruct the entire Hamiltonian family, forming an algebraic variety. We illustrate our presentation with three- and four-dimensional spin chains of difference form with local interactions. Remarkably, all discovered Hamiltonian families form rational varieties.
format Preprint
id arxiv_https___arxiv_org_abs_2503_10469
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Deep Learning based discovery of Integrable Systems
Lal, Shailesh
Majumder, Suvajit
Sobko, Evgeny
High Energy Physics - Theory
Machine Learning
Mathematical Physics
Quantum Algebra
Quantum Physics
We introduce a novel machine learning based framework for discovering integrable models. Our approach first employs a synchronized ensemble of neural networks to find high-precision numerical solution to the Yang-Baxter equation within a specified class. Then, using an auxiliary system of algebraic equations, [Q_2, Q_3] = 0, and the numerical value of the Hamiltonian obtained via deep learning as a seed, we reconstruct the entire Hamiltonian family, forming an algebraic variety. We illustrate our presentation with three- and four-dimensional spin chains of difference form with local interactions. Remarkably, all discovered Hamiltonian families form rational varieties.
title Deep Learning based discovery of Integrable Systems
topic High Energy Physics - Theory
Machine Learning
Mathematical Physics
Quantum Algebra
Quantum Physics
url https://arxiv.org/abs/2503.10469