Skip to content
DraconiticResearch
Search Sources API
203,203 studies31 sourcesUpdated 10 min ago
PreprintarXiv licencearXiv

Lagrangian and Hamiltonian Neural Networks With a Dissipative System

  • V. Rayamajhi
  • J. Singal
Open at sourcePDFDOICite

Abstract

We investigate the applicability of Lagrangian and Hamiltonian Neural Network models to a dissipative system that has explicit time dependence in its Lagrangian, Hamiltonian, and total energy. To do so we consider these neural network models for simulated systems of a harmonic one-dimensional, one-component oscillator with damping, as well as without damping for comparison. We find that both the Lagrangian and Hamiltonian approaches are able to predict the empirical physical behavior of the damped oscillator systems and to effectively ``learn'' to varying degrees the underlying Lagrangians and Hamiltonians, as has previously been shown to be the case with undamped oscillator systems. These investigations elucidate important properties of Lagrangian and Hamiltonian mechanics, including properties that are not manifest when considering systems without explicit time dependence.

Related

  1. Learning Schwarzschild Geodesic Motion with Lagrangian Neural Networks
    Sukru Caglar, Sena Kalabalik, Abdullah Umut Hamzaogullari +1
    arXivPreprintCC BY 4.0Full textGravitation & general relativityarXiv
  2. Recovering Irreducible Three-Body Interactions with Lagrangian Neural Networks
    Sena Kalabalik, Sukru Caglar, Abdullah Umut Hamzaogullari +1
    arXivPreprintCC BY 4.0Full textAtomic, molecular & optical physicsComputational physicsarXiv
  3. Optimal Linear Combination of Hamiltonian Simulation for Dissipative Dynamics
    Hongkang Ni, Lexing Ying
    arXivPreprintarXiv licenceFull textQuantum physics & quantum informationarXiv
  4. Micromagnetic Lagrangian and Hamiltonian Normal-Mode Formulation of Cavity Magnon-Photon Interactions
    Claudio Serpico, Marco Lembo, Giovanni Miano
    arXivPreprintarXiv licenceFull textCondensed matterQuantum physics & quantum informationarXiv
  5. The Gated Quantum Resonator: a reduced-representation Hamiltonian–network framework for gated driven–dissipative quantum systems
    James R F SUTTON
    ChemRxivPreprintCC BYFull textStatistical & nonlinear physicsChemRxiv

Cite

BibTeXRIS
BibTeX
@misc{rayamajhi2026lagrangian,
  title = {{Lagrangian and Hamiltonian Neural Networks With a Dissipative System}},
  author = {V. Rayamajhi and J. Singal},
  howpublished = {arXiv},
  year = {2026},
  month = sep,
  doi = {10.48550/arxiv.2609.31988},
  eprint = {2609.31988},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.31988},
}
RIS
TY  - UNPB
TI  - Lagrangian and Hamiltonian Neural Networks With a Dissipative System
AU  - V. Rayamajhi
AU  - J. Singal
PY  - 2026
DA  - 2026/09/25
PB  - arXiv
DO  - 10.48550/arxiv.2609.31988
UR  - https://arxiv.org/abs/2609.31988
AB  - We investigate the applicability of Lagrangian and Hamiltonian Neural Network models to a dissipative system that has explicit time dependence in its Lagrangian, Hamiltonian, and total energy. To do so we consider these neural network models for simulated systems of a harmonic one-dimensional, one-component oscillator with damping, as well as without damping for comparison. We find that both the Lagrangian and Hamiltonian approaches are able to predict the empirical physical behavior of the damped oscillator systems and to effectively ``learn'' to varying degrees the underlying Lagrangians and Hamiltonians, as has previously been shown to be the case with undamped oscillator systems. These investigations elucidate important properties of Lagrangian and Hamiltonian mechanics, including properties that are not manifest when considering systems without explicit time dependence.
ER  -