Learning Morse Lyapunov functions through invertible neural networks

Towards data-driven stability certificates of dynamical systems, we are witnessing renewed interest in studying and exploiting the structure of Lyapunov functions. Especially Lyapunov functions that are locally quadratic (i.e., Morse) gained popularity ever since it was understood that they can be written as the norm squared of a diffeomorphism. This topological representation alludes to parametrizations using invertible neural networks. In this note we discuss when and how such functions can be learned. In particular, using neural ODEs (NODEs), we characterize Sobolev approximation of these diffeomorphisms on compact sets and show how this naturally relates to stability. We also connect our results to PLNets and supply numerical experiments for illustration.

Authors

Publication Details

Journal
arXiv (Cornell University)
Published
2026-11-16
DOI
https://doi.org/10.48550/arxiv.2611.21030
Primary Topic
Control and Stability of Dynamical Systems
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Learning Morse Lyapunov functions through invertible neural networks

Wouter Jongeneel
arXiv (Cornell University)
Control and Stability of Dynamical Systems
preprint

Learning Morse Lyapunov functions through invertible neural networks

Wouter Jongeneel
preprint en

Abstract

Towards data-driven stability certificates of dynamical systems, we are witnessing renewed interest in studying and exploiting the structure of Lyapunov functions. Especially Lyapunov functions that are locally quadratic (i.e., Morse) gained popularity ever since it was understood that they can be written as the norm squared of a diffeomorphism. This topological representation alludes to parametrizations using invertible neural networks. In this note we discuss when and how such functions can be learned. In particular, using neural ODEs (NODEs), we characterize Sobolev approximation of these diffeomorphisms on compact sets and show how this naturally relates to stability. We also connect our results to PLNets and supply numerical experiments for illustration.

arXiv (Cornell University)
Control and Stability of Dynamical Systems
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon