Convex Formulation of Overparameterized Deep Neural Networks

DOI10.1109/TIT.2022.3163341MaRDI QIDQ5096995zbMATH OpenOpenAlexFDO

Authors

Publication date 19 August 2022

Published in IEEE Transactions on Information Theory (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1911.07626

zbMATH Keywords

fully trainedoverparameterized deep neural networks

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Convex programming (90C25) Applications of mathematical programming (90C90)

Cited in

(5)

• Stabilize deep ResNet with a sharp scaling factor \(\tau\)
• scientific article; zbMATH DE number 7626727 (Why is no real title available?)
• scientific article; zbMATH DE number 7625201 (Why is no real title available?)
• A Note on Lewicki-Sejnowski Gradient for Learning Overcomplete Representations
• A library of mirrors: deep neural nets in low dimensions are convex Lasso models with reflection features

This page was built for publication: Convex Formulation of Overparameterized Deep Neural Networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5096995)