Learning Energy Conserving Dynamics Efficiently with Hamiltonian Gaussian Processes

by   Magnus Ross, et al.

Hamiltonian mechanics is one of the cornerstones of 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.


page 1

page 2

page 3

page 4


Dissipative SymODEN: Encoding Hamiltonian Dynamics with Dissipation and Control into Deep Learning

In this work, we introduce Dissipative SymODEN, a deep learning architec...

Symplectic integration of learned Hamiltonian systems

Hamiltonian systems are differential equations which describe systems in...

Symplectic Gaussian Process Regression of Hamiltonian Flow Maps

We present an approach to construct appropriate and efficient emulators ...

Learning and Interpreting Potentials for Classical Hamiltonian Systems

We consider the problem of learning an interpretable potential energy fu...

Learning Hamiltonians of constrained mechanical systems

Recently, there has been an increasing interest in modelling and computa...

On-the-fly machine learning for parametrization of the effective Hamiltonian

The first-principles-based effective Hamiltonian is widely used to predi...

Please sign up or login with your details

Forgot password? Click here to reset