Data-driven Prediction of General Hamiltonian Dynamics via Learning Exactly-Symplectic Maps

by   Renyi Chen, et al.

We consider the learning and prediction of nonlinear time series generated by a latent symplectic map. A special case is (not necessarily separable) Hamiltonian systems, whose solution flows give such symplectic maps. For this special case, both generic approaches based on learning the vector field of the latent ODE and specialized approaches based on learning the Hamiltonian that generates the vector field exist. Our method, however, is different as it does not rely on the vector field nor assume its existence; instead, it directly learns the symplectic evolution map in discrete time. Moreover, we do so by representing the symplectic map via a generating function, which we approximate by a neural network (hence the name GFNN). This way, our approximation of the evolution map is always exactly symplectic. This additional geometric structure allows the local prediction error at each step to accumulate in a controlled fashion, and we will prove, under reasonable assumptions, that the global prediction error grows at most linearly with long prediction time, which significantly improves an otherwise exponential growth. In addition, as a map-based and thus purely data-driven method, GFNN avoids two additional sources of inaccuracies common in vector-field based approaches, namely the error in approximating the vector field by finite difference of the data, and the error in numerical integration of the vector field for making predictions. Numerical experiments further demonstrate our claims.


page 1

page 2

page 3

page 4


Symplectic integration of learned Hamiltonian systems

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

Leap-frog neural network for learning the symplectic evolution from partitioned data

For the Hamiltonian system, this work considers the learning and predict...

Learning Hamiltonian Systems with Mono-Implicit Runge-Kutta Methods

Numerical integrators could be used to form interpolation conditions whe...

Numerical integration of ODEs while preserving all polynomial first integrals

We present a novel method for solving ordinary differential equations (O...

Deep Hamiltonian networks based on symplectic integrators

HNets is a class of neural networks on grounds of physical prior for lea...

Symplectic Gaussian Process Regression of Hamiltonian Flow Maps

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

Please sign up or login with your details

Forgot password? Click here to reset