mlsanityData to 14 Oct 2026

Hamiltonian Neural PDE Solvers through Functional Approximation

arXiv 2505.13275 ↗First posted 19 May 2025cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Designing neural networks within a Hamiltonian framework offers a principled way to ensure that conservation laws are respected in physical systems. While promising, these capabilities have been largely limited to discrete, analytically solvable systems. In contrast, many physical phenomena are governed by PDEs, which govern infinite-dimensional fields through Hamiltonian functionals and their functional derivatives. Building on prior work, we represent the Hamiltonian functional as a kernel integral parameterized by a neural field, enabling learnable function-to-scalar mappings and the use of automatic differentiation to calculate functional derivatives. This allows for an extension of Hamiltonian mechanics to neural PDE solvers by predicting a functional and learning in the gradient domain. We show that the resulting Hamiltonian Neural Solver (HNS) can be an effective surrogate model through improved stability and conserving energy-like quantities across 1D and 2D PDEs. This ability to respect conservation laws also allows HNS models to better generalize to longer time horizons or unseen initial conditions.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 44 of its 86 references that are in the map. First posted on arXiv 19 May 2025.

Builds on

44 of 86 references.

References · 44

  1. 2020Fourier Neural Operator for Parametric Partial Differential Equationscited by 2,908
  2. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  3. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,333
  4. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,238
  5. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  6. 2020Convolutional Occupancy Networkscited by 761
  7. 2020Neural Operator: Graph Kernel Network for Partial Differential Equationscited by 734
  8. 2019Hamiltonian Neural Networkscited by 712
  9. 2021E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentialscited by 708
  10. 2017SchNet: A continuous-filter convolutional neural network for modeling quantum interactionscited by 571
  11. 2020Directional Message Passing for Molecular Graphscited by 561
  12. 2021Learning the solution operator of parametric partial differential equations with physics-informed DeepOnetscited by 540
32 more
  1. 2021Physics-Informed Neural Operator for Learning Partial Differential Equationscited by 527
  2. 2020Lagrangian Neural Networkscited by 398
  3. 2020Multipole Graph Neural Operator for Parametric Partial Differential Equationscited by 349
  4. 2024Transolver: A Fast Transformer Solver for PDEs on General Geometriescited by 326
  5. 2023Geometry-Informed Neural Operator for Large-Scale 3D PDEscited by 303
  6. 2020Model Reduction and Neural Networks for Parametric PDEscited by 258
  7. 2023PDE-Refiner: Achieving Accurate Long Rollouts with Neural PDE Solverscited by 216
  8. 2019Deep Lagrangian Networks: Using Physics as Model Prior for Deep Learningcited by 212
  9. 2024Poseidon: Efficient Foundation Models for PDEscited by 200
  10. 2022Towards Multi-spatiotemporal-scale Generalized PDE Modelingcited by 197
  11. 2019Symplectic ODE-Net: Learning Hamiltonian Dynamics with Controlcited by 184
  12. 2024DPOT: Auto-Regressive Denoising Operator Transformer for Large-Scale PDE Pre-Trainingcited by 151
  13. 2019Symplectic Recurrent Neural Networkscited by 150
  14. 2021Modulated Periodic Activations for Generalizable Local Functional Representationscited by 140
  15. 2019Hamiltonian Generative Networkscited by 137
  16. 2020Incorporating Symmetry into Deep Dynamics Models for Improved Generalizationcited by 126
  17. 2019Hamiltonian Graph Networks with ODE Integratorscited by 108
  18. 2022Generative Adversarial Neural Operatorscited by 52
  19. 2021Symplectic Learning for Hamiltonian Neural Networkscited by 35
  20. 2021Extending Lagrangian and Hamiltonian Neural Networks with Differentiable Contact Modelscited by 34
  21. 2020Hamiltonian neural networks for solving equations of motioncited by 33
  22. 2022Physics-Embedded Neural Networks: Graph Neural PDE Solvers with Mixed Boundary Conditionscited by 33
  23. 2022Deconstructing the Inductive Biases of Hamiltonian Neural Networkscited by 31
  24. 2025Generative Latent Neural PDE Solver using Flow Matchingcited by 28
  25. 2024Differentiability in Unrolled Training of Neural Physics Simulators on Transient Dynamicscited by 27
  26. 2024Text2PDE: Latent Diffusion Models for Accessible Physics Simulationcited by 25
  27. 2024Lie Algebra Canonicalization: Equivariant Neural Operators under arbitrary Lie Groupscited by 24
  28. 2024An operator learning perspective on parameter-to-observable mapscited by 22
  29. 2024Masked Autoencoders are PDE Learnerscited by 14
  30. 2024Predicting Change, Not States: An Alternate Framework for Neural PDE Surrogatescited by 8
  31. 2023D4FT: A Deep Learning Approach to Kohn-Sham Density Functional Theorycited by 6
  32. 2024Physics-informed Neural Networks for Functional Differential Equations: Cylindrical Approximation and Its Convergence Guaranteescited by 5

Built on by

Not cited yet.