Symplectic Neural Operators for Learning Infinite Dimensional Hamiltonian Systems

• URL: http://arxiv.org/abs/2605.15881v1
• Date: Fri, 15 May 2026 11:58:15 GMT
• Title: Symplectic Neural Operators for Learning Infinite Dimensional Hamiltonian Systems
• Abstract summary: We introduce the Symplectic Neural Operator, a neural operator architecture designed to preserve the symplectic structure intrinsic to Hamiltonian PDEs.<n>We provide a theoretical characterization of their symplecticity and establish a rigorous long-term stability result based on the combination of symplectic structure preservation and learning accuracy.<n> Numerical experiments on canonical Hamiltonian PDEs corroborate this theoretical result and show that SNOs exhibit improved energy behavior compared with non-structure-preserving neural operators.
• Score: 18.71875125509062
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The modeling and simulation of infinite-dimensional Hamiltonian systems are central problems in mathematical physics and engineering, however they pose significant computational and structural challenges for standard data-driven architectures. In this work, we introduce the Symplectic Neural Operator, a neural operator architecture designed to preserve the symplectic structure intrinsic to Hamiltonian PDEs. We provide a theoretical characterization of their symplecticity and establish a rigorous long-term stability result based on the combination of symplectic structure preservation and learning accuracy. Numerical experiments on canonical Hamiltonian PDEs corroborate this theoretical result and show that SNOs exhibit improved energy behavior compared with non-structure-preserving neural operators.

Related papers

• The Kuramoto Neural Operator: Learning to Solve PDEs via Coupled Oscillator Dynamics [46.539149169728624]
  We introduce the Kuramoto Neural Operator (KNO), which represents the solution through the evolution of a latent field of interacting oscillators.<n>KNO achieves strong predictive performance, with improvements over competing approaches.
  arXiv  Detail & Related papers  (2026-08-10T21:11:58Z)
• CoSynFlow: Conformal Symplectic Neural Flows for Cross-System Prediction of Dissipative Hamiltonian Dynamics [8.221727426707526]
  We propose a conformal symplectic neural flow for learning continuous-time solution maps of dissipative Hamiltonian dynamics.<n>CoSynFlow composes symplectic shear maps with explicit conformal scaling, preserving the conformal symplectic structure by construction.
  arXiv  Detail & Related papers  (2026-08-01T10:12:58Z)
• Symplectic Neural Networks for learning Generalized Hamiltonians [5.793251439782513]
  Hamiltonian Neural Networks (HNNs) integrate physical priors into neural models by learning a system's Hamiltonian, improving generalization and sample efficiency.<n>For simulations to faithfully reflect the long-term behavior of Hamiltonian systems, it is essential to use symplectic iteration, which preserve the system's geometric structure.<n>In our work, we explore this alternate method of HNN training under noisy observation of trajectories with our HNN model based on an implicit symplectic integrator.
  arXiv  Detail & Related papers  (2026-06-25T13:36:44Z)
• TIDE: Asymmetric Neural Circuits for Stabilized Temporal Inhibitory-Excitatory Dynamics [51.37317469455798]
  Recent Continuous Thought Machine architecture decouples internal computation from external inputs via neural dynamics.<n>We propose to model neural dynamics using asymmetric Excitatory-Inhibitory (E-I) networks.<n>We introduce Temporal Inhibitory-Excitatory Dynamic Engine (TIDE), a neuro-inspired architecture that computes internal representations through neural dynamics stabilized.
  arXiv  Detail & Related papers  (2026-05-19T05:59:13Z)
• 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)
• Phase space integrity in neural network models of Hamiltonian dynamics: A Lagrangian descriptor approach [0.0]
  We propose Lagrangian Descriptors (LDs) as a diagnostic framework for evaluating neural network models of Hamiltonian systems.<n>By constructing probability density functions weighted by LD values, we embed geometric information into a statistical framework suitable for information-theoretic comparison.<n>For the three-mode nonlinear Schrdinger equation, however, clear differences emerge: symplectic architectures preserve energy but distort phase-space topology, while Reservoir Computing, despite lacking explicit physical constraints, reproduces the homoclinic structure with high fidelity.
  arXiv  Detail & Related papers  (2026-04-01T04:34:54Z)
• 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)
• Unveiling the Actual Performance of Neural-based Models for Equation Discovery on Graph Dynamical Systems [45.11208589443806]
  Kolmogorov-Arnold Networks (KANs) for graphs are designed to exploit their inherent interpretability.<n>KANs successfully identify the underlying symbolic equations, significantly surpassing existing baselines.<n>This study offers a practical guide for researchers, clarifying the trade-offs between model expressivity and interpretability.
  arXiv  Detail & Related papers  (2025-08-25T16:25:50Z)
• Reduced-order modeling of Hamiltonian dynamics based on symplectic neural networks [9.050817345496709]
  We introduce a novel data-driven symplectic induced-order modeling (ROM) framework for high-dimensional Hamiltonian systems.<n>Rom unifies latent-space discovery and dynamics learning within a single, end-to-end neural architecture.
  arXiv  Detail & Related papers  (2025-08-16T05:09:28Z)
• KO: Kinetics-inspired Neural Optimizer with PDE Simulation Approaches [45.173398806932376]
  This paper introduces KO, a novel neural gradient inspired by kinetic theory and partial differential equation (PDE) simulations.<n>We reimagine the dynamics of network parameters as the evolution of a particle system governed by kinetic principles.<n>This physics-driven approach inherently promotes parameter diversity during optimization, mitigating the phenomenon of parameter condensation.
  arXiv  Detail & Related papers  (2025-05-20T18:00:01Z)
• Hamiltonian truncation tensor networks for quantum field theories [42.2225785045544]
  We introduce a tensor network method for the classical simulation of continuous quantum field theories. The method is built on Hamiltonian truncation and tensor network techniques. One of the key developments is the exact construction of matrix product state representations of global projectors.
  arXiv  Detail & Related papers  (2023-12-19T19:00:02Z)
• Neural Operator with Regularity Structure for Modeling Dynamics Driven by SPDEs [70.51212431290611]
  Partial differential equations (SPDEs) are significant tools for modeling dynamics in many areas including atmospheric sciences and physics. We propose the Neural Operator with Regularity Structure (NORS) which incorporates the feature vectors for modeling dynamics driven by SPDEs. We conduct experiments on various of SPDEs including the dynamic Phi41 model and the 2d Navier-Stokes equation.
  arXiv  Detail & Related papers  (2022-04-13T08:53:41Z)
• 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)
• Provably Efficient Neural Estimation of Structural Equation Model: An Adversarial Approach [144.21892195917758]
  We study estimation in a class of generalized Structural equation models (SEMs) We formulate the linear operator equation as a min-max game, where both players are parameterized by neural networks (NNs), and learn the parameters of these neural networks using a gradient descent. For the first time we provide a tractable estimation procedure for SEMs based on NNs with provable convergence and without the need for sample splitting.
  arXiv  Detail & Related papers  (2020-07-02T17:55:47Z)
• Hyperbolic Neural Networks++ [66.16106727715061]
  We generalize the fundamental components of neural networks in a single hyperbolic geometry model, namely, the Poincar'e ball model. Experiments show the superior parameter efficiency of our methods compared to conventional hyperbolic components, and stability and outperformance over their Euclidean counterparts.
  arXiv  Detail & Related papers  (2020-06-15T08:23:20Z)

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.