A Structure-Preserving Kernel Method for Learning Hamiltonian Systems

2024/03/15 by Jianyu Hu, Hu, Jianyu, Juan‐Pablo Ortega +3 · 6 citations
Computer Science · Engineering · Physics and Astronomy · #Control and Stability of Dynamical Systems #Dynamical Systems (math.DS) #FOS: Computer and information sciences #FOS: Mathematics #Gaussian Processes and Bayesian Inference #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Model Reduction and Neural Networks

paper · pdf · doi:10.48550/arxiv.2403.10070

openalex publication_date 2024/03/15 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Cited by

• A kernel method for the learning of Wasserstein geometric flows
• Learning Dynamics from Input-Output Data with Hamiltonian Gaussian Processes
• Data-driven Learning of Interaction Laws in Multispecies Particle Systems with Gaussian Processes: Convergence Theory and Applications
• A study of path measures based on second-order Hamilton--Jacobi equations and their applications in stochastic thermodynamics
• Moment Estimate and Variational Approach for Learning Generalized Diffusion with Non-gradient Structures
• Space filling positionality and the Spiroformer

Related

• A global structure-preserving kernel method for the learning of Poisson systems
• Data-efficient Kernel Methods for Learning Hamiltonian Systems
• On the kernel learning problem
• Structure learning via unstructured kernel-based M-regression
• KAM Theory Meets Statistical Learning Theory: Hamiltonian Neural Networks with Non-Zero Training Loss