Latent Lie-Poisson Neural Networks (LLPNNs): Discovering the motion of Lie-Poisson systems through observable data and latent dynamics

• URL: http://arxiv.org/abs/2607.28939v1
• Date: Fri, 31 Jul 2026 01:38:37 GMT
• Title: Latent Lie-Poisson Neural Networks (LLPNNs): Discovering the motion of Lie-Poisson systems through observable data and latent dynamics
• Abstract summary: We introduce Latent Lie--Poisson Neural Networks (LLPNNs)<n>LLPNNs are a structure-preserving framework for learning Lie--Poisson dynamics directly from observable data.<n>We show excellent long-term predictive accuracy, strong robustness to noise, and competitive performance using only modest and lightweight neural-network architectures.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Structure-preserving neural networks are essential for the long-term prediction of Hamiltonian systems from data. Many important Hamiltonian systems in mechanics and control admit symmetry reduction to Lie--Poisson systems, including rigid bodies, underwater vehicles, fluids, plasmas, and optimal control problems. A fundamental challenge in learning such systems is that their dynamics evolve in momentum variables that are typically unobservable, while available data consist only of observable quantities such as configurations and velocities. In optimal control applications, the situation is further complicated because the latent variables contain unobservable co-states and the Hamiltonian may be degenerate, preventing the existence of a corresponding Lagrangian and rendering the encoder-decoder approaches inapplicable. We introduce Latent Lie--Poisson Neural Networks (LLPNNs), a structure-preserving framework for learning Lie--Poisson dynamics directly from observable data. The proposed approach exploits three geometric ingredients: (i) learning either a Hamiltonian decoder or a pseudo-Lagrangian encoder on the active variables, (ii) constructing latent trajectories through a universal Noether invariant arising from Lie--Poisson symmetry reduction, and (iii) reconstructing observable and latent dynamics through Lie--Poisson flows combined with Magnus-based Lie-group updates. The resulting method preserves the geometric structure and is applicable to both regular and degenerate Hamiltonian systems. We demonstrate the method on three examples: a generalized rigid body on SO(3), Kirchhoff's underwater vehicle on SE(3), and an optimal-control problem for interacting vehicles on $SE(2)^N$. Numerical experiments show excellent long-term predictive accuracy, strong robustness to noise, and competitive performance using only modest datasets and lightweight neural-network architectures.

Related papers

• Learning partially observed systems with neural Hamiltonian ordinary differential equations [41.99844472131922]
  We present neural Hamiltonian ordinary differential equations (NHODE) to learn partially observed dynamical systems from data.<n>The framework is evaluated on systems of increasing complexity, from linear and nonlinear mass-spring systems to the chaotic three-body problem.
  arXiv  Detail & Related papers  (2026-05-22T11:18:39Z)
• 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)
• Physics Informed Constrained Learning of Dynamics from Static Data [8.346864633675414]
  A physics-informed neural network (PINN) models the dynamics of a system by integrating the governing physical laws into the architecture of a neural network.<n>Existing PINN frameworks rely on fully observed time-course data, the acquisition of which could be prohibitive for many systems.<n>In this study, we developed a new PINN learning paradigm, namely Constrained Learning, that enables the approximation of first-order derivatives or motions using non-time course or partially observed data.
  arXiv  Detail & Related papers  (2025-04-17T06:06:53Z)
• CLPNets: Coupled Lie-Poisson Neural Networks for Multi-Part Hamiltonian Systems with Symmetries [0.0]
  We develop a novel method of data-based computation and complete phase space learning of Hamiltonian systems. We derive a novel system of mappings that are built into neural networks for coupled systems. Our method shows good resistance to the curse of dimensionality, requiring only a few thousand data points for all cases studied.
  arXiv  Detail & Related papers  (2024-08-28T22:45:15Z)
• Gibbs-Duhem-Informed Neural Networks for Binary Activity Coefficient Prediction [45.84205238554709]
  We propose Gibbs-Duhem-informed neural networks for the prediction of binary activity coefficients at varying compositions. We include the Gibbs-Duhem equation explicitly in the loss function for training neural networks.
  arXiv  Detail & Related papers  (2023-05-31T07:36:45Z)
• Capturing dynamical correlations using implicit neural representations [85.66456606776552]
  We develop an artificial intelligence framework which combines a neural network trained to mimic simulated data from a model Hamiltonian with automatic differentiation to recover unknown parameters from experimental data. In doing so, we illustrate the ability to build and train a differentiable model only once, which then can be applied in real-time to multi-dimensional scattering data.
  arXiv  Detail & Related papers  (2023-04-08T07:55:36Z)
• ConCerNet: A Contrastive Learning Based Framework for Automated Conservation Law Discovery and Trustworthy Dynamical System Prediction [82.81767856234956]
  This paper proposes a new learning framework named ConCerNet to improve the trustworthiness of the DNN based dynamics modeling. We show that our method consistently outperforms the baseline neural networks in both coordinate error and conservation metrics.
  arXiv  Detail & Related papers  (2023-02-11T21:07:30Z)
• Equivariant Graph Mechanics Networks with Constraints [83.38709956935095]
  We propose Graph Mechanics Network (GMN) which is efficient, equivariant and constraint-aware. GMN represents, by generalized coordinates, the forward kinematics information (positions and velocities) of a structural object. Extensive experiments support the advantages of GMN compared to the state-of-the-art GNNs in terms of prediction accuracy, constraint satisfaction and data efficiency.
  arXiv  Detail & Related papers  (2022-03-12T14:22:14Z)
• Efficient Inference of Flexible Interaction in Spiking-neuron Networks [41.83710212492543]
  We use the nonlinear Hawkes process to model excitatory or inhibitory interactions among neurons. We show our algorithm can estimate the temporal dynamics of interaction and reveal the interpretable functional connectivity underlying neural spike trains.
  arXiv  Detail & Related papers  (2020-06-23T09:10:30Z)

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.