Learning Energy Conserving Dynamics Efficiently with Hamiltonian Gaussian Processes

Published: 09 Mar 2023, Last Modified: 09 Mar 2023Accepted by TMLREveryoneRevisionsBibTeX
Abstract: Hamiltonian mechanics is one of the cornerstones of the natural sciences. Recently there has been significant interest in learning Hamiltonian systems in a free-form way directly from trajectory data. Previous methods have tackled the problem of learning from many short, low-noise trajectories, but learning from a small number of long, noisy trajectories, whilst accounting for model uncertainty has not been addressed. In this work, we present a Gaussian process model for Hamiltonian systems with efficient decoupled parameterisation, and introduce an energy-conserving shooting method that allows robust inference from both short and long trajectories. We demonstrate the method's success in learning Hamiltonian systems in various data settings.
License: Creative Commons Attribution 4.0 International (CC BY 4.0)
Submission Length: Regular submission (no more than 12 pages of main content)
Changes Since Last Submission: Minor edits to text and formatting.
Code: https://github.com/magnusross/hgp
Assigned Action Editor: ~Ole_Winther1
Submission Number: 663