UEPI: Universal Energy-Behavior-Preserving Integrators for Energy Conservative/Dissipative Differential Equations

Abstract

Physical phenomena in the real world are often described by energy-based modeling theories, such as Hamiltonian mechanics or the Landau theory. It is known that physical phenomena based on these theories have an energy conservation law or a dissipation law. Therefore, in the simulations of such physical phenomena, numerical methods that preserve the energy-conservation or dissipation laws are desirable. However, because various energy-behavior-preserving numerical methods have been proposed, it is difficult to discover the best one. In this study, we propose a method for learning highly accurate energy-behavior-preserving integrators from data. Numerical results show that our approach certainly learns energy-behavior-preserving numerical methods that are more accurate than existing numerical methods for various differential equations, including chaotic Hamiltonian systems, dissipative systems, and a nonlinear partial differential equation. We also provide universal approximation theorems for the proposed approach.

Cite

Text

Celledoni et al. "UEPI: Universal  Energy-Behavior-Preserving Integrators for Energy Conservative/Dissipative  Differential Equations." Advances in Neural Information Processing Systems, 2025.

Markdown

[Celledoni et al. "UEPI: Universal  Energy-Behavior-Preserving Integrators for Energy Conservative/Dissipative  Differential Equations." Advances in Neural Information Processing Systems, 2025.](https://mlanthology.org/neurips/2025/celledoni2025neurips-uepi/)

BibTeX

@inproceedings{celledoni2025neurips-uepi,
  title     = {{UEPI: Universal  Energy-Behavior-Preserving Integrators for Energy Conservative/Dissipative  Differential Equations}},
  author    = {Celledoni, Elena and Owren, Brynjulf and Shen, Chong and Xu, Baige and Yaguchi, Takaharu},
  booktitle = {Advances in Neural Information Processing Systems},
  year      = {2025},
  url       = {https://mlanthology.org/neurips/2025/celledoni2025neurips-uepi/}
}