Learning Dynamical Systems from Noisy Data with Inverse-Explicit Integrators

06/06/2023

∙

We introduce the mean inverse integrator (MII), a novel approach to increase the accuracy when training neural networks to approximate vector fields of dynamical systems from noisy data. This method can be used to average multiple trajectories obtained by numerical integrators such as Runge-Kutta methods. We show that the class of mono-implicit Runge-Kutta methods (MIRK) has particular advantages when used in connection with MII. When training vector field approximations, explicit expressions for the loss functions are obtained when inserting the training data in the MIRK formulae, unlocking symmetric and high-order integrators that would otherwise be implicit for initial value problems. The combined approach of applying MIRK within MII yields a significantly lower error compared to the plain use of the numerical integrator without averaging the trajectories. This is demonstrated with experiments using data from several (chaotic) Hamiltonian systems. Additionally, we perform a sensitivity analysis of the loss functions under normally distributed perturbations, supporting the favorable performance of MII.

READ FULL TEXT

Learning Dynamical Systems from Noisy Data with Inverse-Explicit Integrators

Learning Hamiltonian Systems with Mono-Implicit Runge-Kutta Methods

Hamiltonian Neural Networks for solving differential equations

Machine Learning for Initial Value Problems of Parameter-Dependent Dynamical Systems

On the effectiveness of neural priors in modeling dynamical systems

Iterated Vector Fields and Conservatism, with Applications to Federated Learning

Output-weighted and relative entropy loss functions for deep learning precursors of extreme events

Learning Stochastic Dynamical Systems as an Implicit Regularization with Graph Neural Networks

Learning Dynamical Systems from Noisy Data with Inverse-Explicit Integrators

Related Research

Learning Hamiltonian Systems with Mono-Implicit Runge-Kutta Methods

Hamiltonian Neural Networks for solving differential equations

Machine Learning for Initial Value Problems of Parameter-Dependent Dynamical Systems

On the effectiveness of neural priors in modeling dynamical systems

Iterated Vector Fields and Conservatism, with Applications to Federated Learning

Output-weighted and relative entropy loss functions for deep learning precursors of extreme events

Learning Stochastic Dynamical Systems as an Implicit Regularization with Graph Neural Networks