Learning Symmetries of Classical Integrable Systems
Computational Physics
2019-06-12 v1 Machine Learning
Abstract
The solution of problems in physics is often facilitated by a change of variables. In this work we present neural transformations to learn symmetries of Hamiltonian mechanical systems. Maintaining the Hamiltonian structure requires novel network architectures that parametrize symplectic transformations. We demonstrate the utility of these architectures by learning the structure of integrable models. Our work exemplifies the adaptation of neural transformations to a family constrained by more than the condition of invertibility, which we expect to be a common feature of applications of these methods.
Keywords
Cite
@article{arxiv.1906.04645,
title = {Learning Symmetries of Classical Integrable Systems},
author = {Roberto Bondesan and Austen Lamacraft},
journal= {arXiv preprint arXiv:1906.04645},
year = {2019}
}
Comments
8 pages, 5 figures. Presented at the ICML 2019 Workshop on Theoretical Physics for Deep Learning