Contractivity of neural ODEs: an eigenvalue optimization problem

DOI10.1090/MCOM/4059MaRDI QIDQ6927797zbMATH OpenFDO

Authors Nicola Guglielmi, Arturo De Marinis, Anton Savostianov, Francesco Tudisco

Publication date 18 September 2025

Published in Mathematics of Computation (Search for Journal in Brave)

zbMATH Keywords

eigenvalue optimizationgradient systemslogarithmic normneural ODEsResNetcontractivity in spectral norm

Mathematics Subject Classification ID

Numerical optimization and variational techniques (65K10) Artificial neural networks and deep learning (68T07) Numerical methods for initial value problems involving ordinary differential equations (65L05)

Cites work

• scientific article; zbMATH DE number 3239038 (Why is no real title available?)
• Designing stable neural networks using convex analysis and ODEs
• Dynamical Systems–Based Neural Networks
• Solving Ordinary Differential Equations I
• Stable architectures for deep neural networks
• Structure-preserving deep learning
• The logarithmic norm. History and modern theory

Cited in

(1)

• The vanishing gradient problem for stiff neural differential equations

This page was built for publication: Contractivity of neural ODEs: an eigenvalue optimization problem

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6927797)