Learning Hamiltonian dynamics with reproducing kernel Hilbert spaces and random features

DOI10.1016/J.EJCON.2024.101128MaRDI QIDQ6669750zbMATH OpenFDO

Authors Torbjørn Smith, O. Egeland

Publication date 22 January 2025

Published in European Journal of Control (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/J.EJCON.2024.101128

zbMATH Keywords

machine learningreproducing kernel Hilbert spacesystem identification

Mathematics Subject Classification ID

Linear operators in reproducing-kernel Hilbert spaces (including de Branges, de Branges-Rovnyak, and other structured spaces) (47B32) Learning and adaptive systems in artificial intelligence (68T05) Operator-theoretic methods (93B28) System identification (93B30)

Recommendations

• Symplectic neural networks in Taylor series form for Hamiltonian systems
• Symmetry preservation in Hamiltonian systems: simulation and learning
• Symplectic learning for Hamiltonian neural networks
• Learning Hamiltonians of constrained mechanical systems

Cites work

• Data-driven science and engineering. Machine learning, dynamical systems, and control
• Gaussian processes for machine learning.
• Geometric Numerical Integration
• scientific article; zbMATH DE number 1804115 (Why is no real title available?)
• scientific article; zbMATH DE number 194544 (Why is no real title available?)
• Kernel-Based Models for System Analysis
• Numerically optimal Runge-Kutta pairs with interpolants
• On Learning Vector-Valued Functions
• Symplectic Gaussian process regression of maps in Hamiltonian systems
• Theory of Reproducing Kernels
• VECTOR VALUED REPRODUCING KERNEL HILBERT SPACES AND UNIVERSALITY

Cited in

(5)

• Pseudo-Hamiltonian system identification
• Bayesian identification of nonseparable Hamiltonians with multiplicative noise using deep learning and reduced-order modeling
• Symmetry preservation in Hamiltonian systems: simulation and learning
• A combined estimator for nonlinear system identification via LPV approximations
• Symplecticity-preserving prediction of Hamiltonian dynamics by generalized kernel interpolation

This page was built for publication: Learning Hamiltonian dynamics with reproducing kernel Hilbert spaces and random features

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6669750)