Frequency-Separable Hamiltonian Neural Network for Multi-Timescale Dynamics

• URL: http://arxiv.org/abs/2603.06354v1
• Date: Fri, 06 Mar 2026 15:06:08 GMT
• Title: Frequency-Separable Hamiltonian Neural Network for Multi-Timescale Dynamics
• Abstract summary: Hamiltonian Neural Networks fail to capture complex temporal dynamics spanning multiple timescales.<n>We introduce the Frequency-Separable Hamiltonian Neural Network (FS-HNN), which parameterizes the system Hamiltonian using multiple networks.<n>We extend this framework to partial differential equations by learning a state- and boundary-conditioned symplectic operators.
• Score: 2.327847860343284
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: While Hamiltonian mechanics provides a powerful inductive bias for neural networks modeling dynamical systems, Hamiltonian Neural Networks and their variants often fail to capture complex temporal dynamics spanning multiple timescales. This limitation is commonly linked to the spectral bias of deep neural networks, which favors learning low-frequency, slow-varying dynamics. Prior approaches have sought to address this issue through symplectic integration schemes that enforce energy conservation or by incorporating geometric constraints to impose structure on the configuration-space. However, such methods either remain limited in their ability to fully capture multiscale dynamics or require substantial domain specific assumptions. In this work, we exploit the observation that Hamiltonian functions admit decompositions into explicit fast and slow modes and can be reconstructed from these components. We introduce the Frequency-Separable Hamiltonian Neural Network (FS-HNN), which parameterizes the system Hamiltonian using multiple networks, each governed by Hamiltonian dynamics and trained on data sampled at distinct timescales. We further extend this framework to partial differential equations by learning a state- and boundary-conditioned symplectic operators. Empirically, we show that FS-HNN improves long-horizon extrapolation performance on challenging dynamical systems and generalizes across a broad range of ODE and PDE problems.

Related papers

• Extrapolating the emergence of Hamiltonian chaos with random-feature Hamiltonian neural networks [0.0]
  We show that a Hamiltonian neural network can extrapolate from predominantly regular dynamics into a broad chaotic sea absent from training.<n>To our knowledge, this is the first demonstration that a learned Hamiltonian can qualitatively extrapolate from predominantly regular dynamics into a broad chaotic sea absent from training.
  arXiv  Detail & Related papers  (2026-07-31T03:00:57Z)
• Identifying the nonlinear string dynamics with port-Hamiltonian neural networks [0.30586855806896035]
  We show how to learn the nonlinear string dynamics from data in a physically-consistent framework through a PHNN extension to PDEs.<n>This approach outperforms baseline, non-physics-informed methods in terms of both accuracy and interpretability.
  arXiv  Detail & Related papers  (2026-05-12T22:01:16Z)
• Learning Hamiltonian Dynamics at Scale: A Differential-Geometric Approach [15.500592651570384]
  This paper introduces a novel physics-inspired neural network that combines the conservation laws of Hamiltonian mechanics with the scalability of model order reduction.<n>Our experiments demonstrate that RO-HNN provides physically-consistent, stable, and generalizable predictions of complex high-dimensional dynamics.
  arXiv  Detail & Related papers  (2025-09-29T11:36:35Z)
• Kolmogorov-Arnold Representation for Symplectic Learning: Advancing Hamiltonian Neural Networks [4.130455471816662]
  Hamiltonian Neural Networks (HNNs) ensure energy conservation by learning Hamiltonian functions directly from data.<n>Our approach exploits localized function approximations to better capture high-frequency and multi-scale dynamics.<n>The networks preserve the symplectic form of Hamiltonian systems, and thus maintain interpretability and physical consistency.
  arXiv  Detail & Related papers  (2025-08-26T20:22:33Z)
• Fractional Spike Differential Equations Neural Network with Efficient Adjoint Parameters Training [63.3991315762955]
  Spiking Neural Networks (SNNs) draw inspiration from biological neurons to create realistic models for brain-like computation.<n>Most existing SNNs assume a single time constant for neuronal membrane voltage dynamics, modeled by first-order ordinary differential equations (ODEs) with Markovian characteristics.<n>We propose the Fractional SPIKE Differential Equation neural network (fspikeDE), which captures long-term dependencies in membrane voltage and spike trains through fractional-order dynamics.
  arXiv  Detail & Related papers  (2025-07-22T18:20:56Z)
• Fourier Neural Operators for Learning Dynamics in Quantum Spin Systems [77.88054335119074]
  We use FNOs to model the evolution of random quantum spin systems. We apply FNOs to a compact set of Hamiltonian observables instead of the entire $2n$ quantum wavefunction.
  arXiv  Detail & Related papers  (2024-09-05T07:18:09Z)
• Applications of Machine Learning to Modelling and Analysing Dynamical Systems [0.0]
  We propose an architecture which combines existing Hamiltonian Neural Network structures into Adaptable Symplectic Recurrent Neural Networks. This architecture is found to significantly outperform previously proposed neural networks when predicting Hamiltonian dynamics. We show that this method works efficiently for single parameter potentials and provides accurate predictions even over long periods of time.
  arXiv  Detail & Related papers  (2023-07-22T19:04:17Z)
• How neural networks learn to classify chaotic time series [77.34726150561087]
  We study the inner workings of neural networks trained to classify regular-versus-chaotic time series. We find that the relation between input periodicity and activation periodicity is key for the performance of LKCNN models.
  arXiv  Detail & Related papers  (2023-06-04T08:53:27Z)
• Dynamics with autoregressive neural quantum states: application to critical quench dynamics [41.94295877935867]
  We present an alternative general scheme that enables one to capture long-time dynamics of quantum systems in a stable fashion. We apply the scheme to time-dependent quench dynamics by investigating the Kibble-Zurek mechanism in the two-dimensional quantum Ising model.
  arXiv  Detail & Related papers  (2022-09-07T15:50:00Z)
• Momentum Diminishes the Effect of Spectral Bias in Physics-Informed Neural Networks [72.09574528342732]
  Physics-informed neural network (PINN) algorithms have shown promising results in solving a wide range of problems involving partial differential equations (PDEs) They often fail to converge to desirable solutions when the target function contains high-frequency features, due to a phenomenon known as spectral bias. In the present work, we exploit neural tangent kernels (NTKs) to investigate the training dynamics of PINNs evolving under gradient descent with momentum (SGDM)
  arXiv  Detail & Related papers  (2022-06-29T19:03:10Z)
• Learning Trajectories of Hamiltonian Systems with Neural Networks [81.38804205212425]
  We propose to enhance Hamiltonian neural networks with an estimation of a continuous-time trajectory of the modeled system. We demonstrate that the proposed integration scheme works well for HNNs, especially with low sampling rates, noisy and irregular observations.
  arXiv  Detail & Related papers  (2022-04-11T13:25:45Z)
• Nonseparable Symplectic Neural Networks [23.77058934710737]
  We propose a novel neural network architecture, Nonseparable Symplectic Neural Networks (NSSNNs) NSSNNs uncover and embed the symplectic structure of a nonseparable Hamiltonian system from limited observation data. We show the unique computational merits of our approach to yield long-term, accurate, and robust predictions for large-scale Hamiltonian systems.
  arXiv  Detail & Related papers  (2020-10-23T19:50:13Z)
• Sparse Symplectically Integrated Neural Networks [15.191984347149667]
  We introduce Sparselectically Integrated Neural Networks (SSINNs) SSINNs are a novel model for learning Hamiltonian dynamical systems from data. We evaluate SSINNs on four classical Hamiltonian dynamical problems.
  arXiv  Detail & Related papers  (2020-06-10T03:33:37Z)
• Liquid Time-constant Networks [117.57116214802504]
  We introduce a new class of time-continuous recurrent neural network models. Instead of declaring a learning system's dynamics by implicit nonlinearities, we construct networks of linear first-order dynamical systems. These neural networks exhibit stable and bounded behavior, yield superior expressivity within the family of neural ordinary differential equations.
  arXiv  Detail & Related papers  (2020-06-08T09:53:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.