paper-with-me

Papers

Data-efficient Kernel Methods for Learning Hamiltonian Systems

2025-09-21 · Yasamin Jalalian, Mostafa Samir, Boumediene Hamzi, Peyman Tavallali, Houman Owhadi arxiv

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.

📄 PDF Abstract BibTeX arXiv:2509.17154

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Learning Hamiltonian Dynamics with Reproducing Kernel Hilbert Spaces and Random Features

2024-04-11 · Torbjørn Smith, Olav Egeland

A method for learning Hamiltonian dynamics from a limited and noisy dataset is proposed. The method learns a Hamiltonian vector field on a reproducing kernel Hilbert space (RKHS) of inherently Hamiltonian vector fields, …

Learning of Hamiltonian Dynamics with Reproducing Kernel Hilbert Spaces

2023-12-15 · Torbjørn Smith, Olav Egeland

This paper presents a method for learning Hamiltonian dynamics from a limited set of data points. The Hamiltonian vector field is found by regularized optimization over a reproducing kernel Hilbert space of vector fields…

Learning ground states of gapped quantum Hamiltonians with Kernel Methods

2023-03-15 · Clemens Giuliani, Filippo Vicentini, Riccardo Rossi, Giuseppe Carleo

Neural network approaches to approximate the ground state of quantum hamiltonians require the numerical solution of a highly nonlinear optimization problem. We introduce a statistical learning approach that makes the opt…

Learning dissipative Hamiltonian dynamics with reproducing kernel Hilbert spaces and random Fourier features

2024-10-24 · Torbjørn Smith, Olav Egeland

This paper presents a new method for learning dissipative Hamiltonian dynamics from a limited and noisy dataset. The method uses the Helmholtz decomposition to learn a vector field as the sum of a symplectic and a dissip…

A Structure-Preserving Kernel Method for Learning Hamiltonian Systems

2024-03-15 · Jianyu Hu, Juan-Pablo Ortega, Daiying Yin

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 …

regression