Data-efficient Kernel Methods for Learning Hamiltonian Systems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jalalian, Yasamin, Samir, Mostafa, Hamzi, Boumediene, Tavallali, Peyman, Owhadi, Houman
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916959827787776
author Jalalian, Yasamin
Samir, Mostafa
Hamzi, Boumediene
Tavallali, Peyman
Owhadi, Houman
author_facet Jalalian, Yasamin
Samir, Mostafa
Hamzi, Boumediene
Tavallali, Peyman
Owhadi, Houman
contents Hamiltonian dynamics describe a wide range of physical systems. As such, data-driven simulations of Hamiltonian systems are important for many scientific and engineering problems. In this work, we propose kernel-based methods for identifying and forecasting Hamiltonian systems directly from data. We present two approaches: a two-step method that reconstructs trajectories before learning the Hamiltonian, and a one-step method that jointly infers both. Across several benchmark systems, including mass-spring dynamics, a nonlinear pendulum, and the Henon-Heiles system, we demonstrate that our framework achieves accurate, data-efficient predictions and outperforms two-step kernel-based baselines, particularly in scarce-data regimes, while preserving the conservation properties of Hamiltonian dynamics. Moreover, our methodology provides theoretical a priori error estimates, ensuring reliability of the learned models. We also provide a more general, problem-agnostic numerical framework that goes beyond Hamiltonian systems and can be used for data-driven learning of arbitrary dynamical systems.
format Preprint
id arxiv_https___arxiv_org_abs_2509_17154
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Data-efficient Kernel Methods for Learning Hamiltonian Systems
Jalalian, Yasamin
Samir, Mostafa
Hamzi, Boumediene
Tavallali, Peyman
Owhadi, Houman
Numerical Analysis
Machine Learning
Dynamical Systems
Hamiltonian dynamics describe a wide range of physical systems. As such, data-driven simulations of Hamiltonian systems are important for many scientific and engineering problems. In this work, we propose kernel-based methods for identifying and forecasting Hamiltonian systems directly from data. We present two approaches: a two-step method that reconstructs trajectories before learning the Hamiltonian, and a one-step method that jointly infers both. Across several benchmark systems, including mass-spring dynamics, a nonlinear pendulum, and the Henon-Heiles system, we demonstrate that our framework achieves accurate, data-efficient predictions and outperforms two-step kernel-based baselines, particularly in scarce-data regimes, while preserving the conservation properties of Hamiltonian dynamics. Moreover, our methodology provides theoretical a priori error estimates, ensuring reliability of the learned models. We also provide a more general, problem-agnostic numerical framework that goes beyond Hamiltonian systems and can be used for data-driven learning of arbitrary dynamical systems.
title Data-efficient Kernel Methods for Learning Hamiltonian Systems
topic Numerical Analysis
Machine Learning
Dynamical Systems
url https://arxiv.org/abs/2509.17154