UEPI: Universal Energy-Behavior-Preserving Integrators for Energy Conservative/Dissipative Differential Equations
Elena Celledoni, Brynjulf Owren, Chong Shen, Baige Xu, Takaharu Yaguchi
摘要
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.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
它引用的顶会 Paper5
- Fourier Neural Operator for Parametric Partial Differential EquationsZongyi Li, Nikola Borislavov Kovachki, Kamyar Azizzadenesheli, Burigede Liu 等ICLR 2021 · 被引用 3,911 次
- Symplectic Recurrent Neural NetworksZhengdao Chen, Jianyu Zhang, Martín Arjovsky, Léon BottouICLR 2020 · 被引用 261 次
- Neural Flows: Efficient Alternative to Neural ODEsMarin Bilos, Johanna Sommer, Syama Sundar Rangapuram, Tim Januschowski 等NeurIPS 2021 · 被引用 151 次
- Time-Reversal Symmetric ODE NetworkIn Huh, Eunho Yang, Sung Ju Hwang, Jinwoo ShinNeurIPS 2020 · 被引用 29 次
- Neural Dynamics on Complex NetworksChengxi Zang, Fei WangKDD 2020 · 被引用 4 次
相关 Paper
- Deep Energy-based Modeling of Discrete-Time PhysicsTakashi Matsubara, Ai Ishikawa, Takaharu YaguchiNeurIPS 2020 · 被引用 46 次
- Hamiltonian Neural PDE Solvers through Functional ApproximationAnthony Y. Zhou, Amir Barati FarimaniNeurIPS 2025 · 被引用 1 次
- Sparse Symplectically Integrated Neural NetworksDaniel M. DiPietro, Shiying Xiong, Bo ZhuNeurIPS 2020 · 被引用 39 次
- FINDE: Neural Differential Equations for Finding and Preserving Invariant QuantitiesTakashi Matsubara, Takaharu YaguchiICLR 2023 · 被引用 4 次
- Harnessing the Power of Neural Operators with Automatically Encoded Conservation LawsNing Liu, Yiming Fan, Xianyi Zeng, Milan Klöwer 等ICML 2024 · 被引用 20 次
