Understanding deep representation learning via layerwise feature compression and discrimination

MaRDI QIDQ7308328zbMATH OpenFDO

Authors Peng Wang, Xiao Li, Can Yaras, Zhihui Zhu, Laura Balzano, Qing Qu, Wei Hu

Publication date 4 August 2026

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/v26/24-0047.html

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Artificial neural networks and deep learning (68T07)

Cites work

• A mathematical theory of semantic development in deep neural networks
• Benign overfitting in linear regression
• Complete dictionary learning via ^4-norm maximization over the orthogonal group
• Complete Dictionary Recovery Over the Sphere I: Overview and the Geometric Picture
• Effects of depth, width, and initialization: a convergence analysis of layer-wise training for deep linear neural networks
• Exploring deep neural networks via layer-peeled model: minority collapse in imbalanced training
• scientific article; zbMATH DE number 47363 (Why is no real title available?)
• Learning deep linear neural networks: Riemannian gradient flows and convergence to global minimizers
• Optimally sparse representation in general (nonorthogonal) dictionaries via ℓ ¹ minimization
• Prevalence of neural collapse during the terminal phase of deep learning training
• Reconciling modern machine-learning practice and the classical bias-variance trade-off
• The implicit bias of gradient descent on separable data

This page was built for publication: Understanding deep representation learning via layerwise feature compression and discrimination

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7308328)