Singular value perturbation and deep network optimization

DOI10.1007/s00365-022-09601-5OpenAlexW4310276356MaRDI QIDQ2700883

Randall Balestriero, Richard G. Baraniuk, Rudolf H. Riedi

Publication date: 27 April 2023

Published in: Constructive Approximation (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2203.03099

zbMATH Keywords

perturbation theorysingular valuesdeep learningoptimization landscape

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Perturbation theory of linear operators (47A55)

Cites Work

• The right tail exponent of the Tracy-Widom \(\beta\) distribution
• Level-spacing distributions and the Airy kernel
• Adaptive estimation of a quadratic functional by model selection.
• The variation of the spectrum of a normal matrix
• Group Invariant Scattering
• Eigenvalues and Condition Numbers of Random Matrices
• Unnamed Item
• Unnamed Item

This page was built for publication: Singular value perturbation and deep network optimization