Interpretable global minima of deep ReLU neural networks on sequentially separable data

MaRDI QIDQ6887366zbMATH OpenFDO

Authors Thomas Chen, Patrícia Muñoz Ewald

Publication date 9 December 2025

Published in Journal of Machine Learning Research (JMLR) (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://jmlr.org/papers/v26/24-1516.html

zbMATH Keywords

classificationclusterdatadeep learningglobal minimaneural network

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Artificial neural networks and deep learning (68T07)

Cites work

• Generalized Inverses of Linear Transformations
• scientific article; zbMATH DE number 7064043 (Why is no real title available?)
• Neural collapse with unconstrained features
• On non-approximability of zero loss global \(\mathcal{L}^2\) minimizers by gradient descent in deep learning
• Prevalence of neural collapse during the terminal phase of deep learning training

Cited in

(1)

• Geometric structure of shallow neural networks and constructive \(\mathcal{L}^2\) cost minimization

This page was built for publication: Interpretable global minima of deep ReLU neural networks on sequentially separable data

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6887366)