Deep Learning based discovery of Integrable Systems
This work addresses the discovery of integrable systems in mathematical physics, presenting a novel computational approach that could accelerate research in this domain.
The authors tackled the problem of discovering integrable models by introducing a machine learning framework that uses neural networks to solve the Yang-Baxter equation and reconstruct Hamiltonian families, demonstrating it on three- and four-dimensional spin chains with all discovered families forming rational varieties.
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.