English

Learning reversible symplectic dynamics

Machine Learning 2022-04-28 v1 Dynamical Systems Computational Physics

Abstract

Time-reversal symmetry arises naturally as a structural property in many dynamical systems of interest. While the importance of hard-wiring symmetry is increasingly recognized in machine learning, to date this has eluded time-reversibility. In this paper we propose a new neural network architecture for learning time-reversible dynamical systems from data. We focus in particular on an adaptation to symplectic systems, because of their importance in physics-informed learning.

Keywords

Cite

@article{arxiv.2204.12323,
  title  = {Learning reversible symplectic dynamics},
  author = {Riccardo Valperga and Kevin Webster and Victoria Klein and Dmitry Turaev and Jeroen S. W. Lamb},
  journal= {arXiv preprint arXiv:2204.12323},
  year   = {2022}
}

Comments

Published at the 4th Annual Learning for Dynamics & Control Conference

R2 v1 2026-06-24T10:59:03.529Z