Guardado en:
Detalles Bibliográficos
Autores principales: Hu, Jianyu, Ortega, Juan-Pablo, Yin, Daiying
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2403.10070
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913775695691776
author Hu, Jianyu
Ortega, Juan-Pablo
Yin, Daiying
author_facet Hu, Jianyu
Ortega, Juan-Pablo
Yin, Daiying
contents A structure-preserving kernel ridge regression method is presented that allows the recovery of nonlinear Hamiltonian functions out of datasets made of noisy observations of Hamiltonian vector fields. The method proposes a closed-form solution that yields excellent numerical performances that surpass other techniques proposed in the literature in this setup. From the methodological point of view, the paper extends kernel regression methods to problems in which loss functions involving linear functions of gradients are required and, in particular, a differential reproducing property and a Representer Theorem are proved in this context. The relation between the structure-preserving kernel estimator and the Gaussian posterior mean estimator is analyzed. A full error analysis is conducted that provides convergence rates using fixed and adaptive regularization parameters. The good performance of the proposed estimator together with the convergence rate is illustrated with various numerical experiments.
format Preprint
id arxiv_https___arxiv_org_abs_2403_10070
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Structure-Preserving Kernel Method for Learning Hamiltonian Systems
Hu, Jianyu
Ortega, Juan-Pablo
Yin, Daiying
Machine Learning
Dynamical Systems
A structure-preserving kernel ridge regression method is presented that allows the recovery of nonlinear Hamiltonian functions out of datasets made of noisy observations of Hamiltonian vector fields. The method proposes a closed-form solution that yields excellent numerical performances that surpass other techniques proposed in the literature in this setup. From the methodological point of view, the paper extends kernel regression methods to problems in which loss functions involving linear functions of gradients are required and, in particular, a differential reproducing property and a Representer Theorem are proved in this context. The relation between the structure-preserving kernel estimator and the Gaussian posterior mean estimator is analyzed. A full error analysis is conducted that provides convergence rates using fixed and adaptive regularization parameters. The good performance of the proposed estimator together with the convergence rate is illustrated with various numerical experiments.
title A Structure-Preserving Kernel Method for Learning Hamiltonian Systems
topic Machine Learning
Dynamical Systems
url https://arxiv.org/abs/2403.10070