DeepAI AI Chat
Log In Sign Up

Variational integration of learned dynamical systems

by   Sina Ober-Blöbaum, et al.
Universität Paderborn

The principle of least action is one of the most fundamental physical principle. It says that among all possible motions connecting two points in a phase space, the system will exhibit those motions which extremise an action functional. Many qualitative features of dynamical systems, such as the presence of conservation laws and energy balance equations, are related to the existence of an action functional. Incorporating variational structure into learning algorithms for dynamical systems is, therefore, crucial in order to make sure that the learned model shares important features with the exact physical system. In this paper we show how to incorporate variational principles into trajectory predictions of learned dynamical systems. The novelty of this work is that (1) our technique relies only on discrete position data of observed trajectories. Velocities or conjugate momenta do not need to be observed or approximated and no prior knowledge about the form of the variational principle is assumed. Instead, they are recovered using backward error analysis. (2) Moreover, our technique compensates discretisation errors when trajectories are computed from the learned system. This is important when moderate to large step-sizes are used and high accuracy is required. For this, we introduce and rigorously analyse the concept of inverse modified Lagrangians by developing an inverse version of variational backward error analysis. (3) Finally, we introduce a method to perform system identification from position observations only, based on variational backward error analysis.


Symplectic integration of learned Hamiltonian systems

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

Discrete Lagrangian Neural Networks with Automatic Symmetry Discovery

By one of the most fundamental principles in physics, a dynamical system...

Hamiltonian Neural Networks for solving differential equations

There has been a wave of interest in applying machine learning to study ...

An Energy-based Approach to Ensure the Stability of Learned Dynamical Systems

Non-linear dynamical systems represent a compact, flexible, and robust t...

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

We consider initial value problems of nonlinear dynamical systems, which...

The Dynamical Principles of Storytelling

When considering the opening part of 1800 short stories, we find that th...

Connecting beams and continua: variational basis and mathematical analysis

We present a new variational principle for linking models of beams and d...