mlsanityData to 14 Oct 2026

Learning reversible symplectic dynamics

arXiv 2204.12323 ↗First posted 26 Apr 2022stat.ML math.DS physics.comp-phcited by 11

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 4 of its 13 references that are in the map. First posted on arXiv 26 Apr 2022.

Builds on

4 of 13 references.

References · 4

  1. 2016Density estimation using Real NVPcited by 2,042
  2. 2019Hamiltonian Neural Networkscited by 712
  3. 2020Coupling-based Invertible Neural Networks Are Universal Diffeomorphism Approximatorscited by 85
  4. 2021Port-Hamiltonian Neural Networks for Learning Explicit Time-Dependent Dynamical Systemscited by 67

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 3; 2024: 5; 2025: 1.

11 papers.

  1. 2024Space-Time Continuous PDE Forecasting using Equivariant Neural Fieldscited by 18
  2. 2023Constructing Custom Thermodynamics Using Deep Learningcited by 17
  3. 2022Lie Group Forced Variational Integrator Networks for Learning and Control of Robot Systemscited by 7
  4. 2022Approximation of nearly-periodic symplectic maps via structure-preserving neural networkscited by 6
  5. 2023Learning Lie Group Symmetry Transformations with Neural Networkscited by 6
  6. 2024Projected Neural Differential Equations for Learning Constrained Dynamicscited by 5
  7. 2023TANGO: Time-Reversal Latent GraphODE for Multi-Agent Dynamical Systemscited by 4
  8. 2024Symplectic Neural Networks Based on Dynamical Systemscited by 4
  9. 2024Learning Generalized Hamiltonians using fully Symplectic Mappingscited by 2
  10. 2025Data-efficient Kernel Methods for Learning Hamiltonian Systemscited by 2
  11. 2024Ai-Sampler: Adversarial Learning of Markov kernels with involutive mapscited by 1