Deep Learning based discovery of Integrable Systems

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.

@article{lal2025_2503.10469,
  title={ Deep Learning based discovery of Integrable Systems },
  author={ Shailesh Lal and Suvajit Majumder and Evgeny Sobko },
  journal={arXiv preprint arXiv:2503.10469},
  year={ 2025 }
}