Structure-preserving dimensionality reduction for learning Hamiltonian dynamics

DOI10.1016/J.JCP.2025.113832MaRDI QIDQ6990556zbMATH OpenFDO

Authors Janis Bajars, Dāvis Kalvāns

Publication date 29 April 2025

Published in Journal of Computational Physics (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/J.JCP.2025.113832

zbMATH Keywords

deep learningHamiltonian dynamicslearning localized wave solutionsstructure-preserving neural networkssymplectic dimensionality reduction

Mathematics Subject Classification ID

Numerical methods for inverse problems for initial value and initial-boundary value problems involving PDEs (65M32) Numerical methods for Hamiltonian systems including symplectic integrators (65P10) Artificial neural networks and deep learning (68T07)

Cites work

• Breathers and kinks in a simulated crystal experiment
• Data-driven intrinsic localized mode detection and classification in one-dimensional crystal lattice model
• Data-driven science and engineering. Machine learning, dynamical systems, and control
• Discrete breathers with dissipation
• Frequency-momentum representation of moving breathers in a two dimensional hexagonal lattice
• Geometric Numerical Integration
• Hamiltonian Deep Neural Networks Guaranteeing Nonvanishing Gradients by Design
• Hamiltonian operator inference: physics-preserving learning of reduced-order models for canonical Hamiltonian systems
• scientific article; zbMATH DE number 194356 (Why is no real title available?)
• scientific article; zbMATH DE number 6159604 (Why is no real title available?)
• Locally-symplectic neural networks for learning volume-preserving dynamics
• Multilayer feedforward networks are universal approximators
• Nonlinear propagating localized modes in a 2D hexagonal crystal lattice
• Structure preserving model reduction of parametric Hamiltonian systems
• Structure-preserving deep learning
• Structure-preserving neural networks
• Symplectic model reduction of Hamiltonian systems
• Sympnets: intrinsic structure-preserving symplectic networks for identifying Hamiltonian systems
• VPNets: volume-preserving neural networks for learning source-free dynamics

This page was built for publication: Structure-preserving dimensionality reduction for learning Hamiltonian dynamics

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6990556)