Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Mebratie, Meskerem Abebaw, Nather, Rüdiger, von Rudorff, Guido Falk, Seiler, Werner M.
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2405.20857
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916267576786944
author Mebratie, Meskerem Abebaw
Nather, Rüdiger
von Rudorff, Guido Falk
Seiler, Werner M.
author_facet Mebratie, Meskerem Abebaw
Nather, Rüdiger
von Rudorff, Guido Falk
Seiler, Werner M.
contents Conservation laws are of great theoretical and practical interest. We describe a novel approach to machine learning conservation laws of finite-dimensional dynamical systems using trajectory data. It is the first such 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 here a simple approach minimising the length of the coefficient vector to discover a single conservation law.
format Preprint
id arxiv_https___arxiv_org_abs_2405_20857
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Machine Learning Conservation Laws of Dynamical systems
Mebratie, Meskerem Abebaw
Nather, Rüdiger
von Rudorff, Guido Falk
Seiler, Werner M.
Computational Physics
Conservation laws are of great theoretical and practical interest. We describe a novel approach to machine learning conservation laws of finite-dimensional dynamical systems using trajectory data. It is the first such 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 here a simple approach minimising the length of the coefficient vector to discover a single conservation law.
title Machine Learning Conservation Laws of Dynamical systems
topic Computational Physics
url https://arxiv.org/abs/2405.20857