Machine learning conservation laws of dynamical systems
Open Access
- 13 February 2025
- journal article
- Published by American Physical Society (APS) in Physical Review E
- Vol. 111 (2) , 025305
Abstract
Conservation laws are of great theoretical and practical interest. We describe an alternative approach to machine learning conservation laws of finite-dimensional dynamical systems using trajectory data. It is a unique approach based on kernel methods instead of neural networks which leads to lower computational costs and requires a lower amount of training data. We propose the use of an “indeterminate” form of kernel ridge regression where the labels still have to be found by additional conditions. We use a simple approach minimizing the length of the coefficient vector to discover a single conservation law. Published by the American Physical Society 2025Keywords
All Related Versions
Funding Information
- Deutsche Forschungsgemeinschaft
This publication has 30 references indexed in Scilit:
- Foundations of Chemical Reaction Network Theory2019
- Detection of Hopf bifurcations in chemical reaction networks using convex coordinatesJournal of Computational Physics, 2015
- Kernel Methods and Machine Learning2014
- For most large underdetermined systems of linear equations the minimal 𝓁1‐norm solution is also the sparsest solutionCommunications on Pure and Applied Mathematics, 2006
- Stable signal recovery from incomplete and inaccurate measurementsCommunications on Pure and Applied Mathematics, 2006
- Kernel Methods for Pattern Analysis2004
- Conservation laws for Lotka–Volterra modelsMathematical Methods in the Applied Sciences, 2003
- Introduction to Smooth Manifolds2003
- Applications of Lie Groups to Differential Equations1986
- Computer Algebra1982