Dynamics in Deep Classifiers Trained with the Square Loss: Normalization, Low Rank, Neural Collapse, and Generalization Bounds

We overview several properties—old and new—of training overparameterized deep networks under the square loss. We first consider a model of the dynamics of gradient flow under the square loss in deep homogeneous rectified linear unit networks. We study the convergence to a solution with the absolute...

Descripción completa

Detalles Bibliográficos
Autores principales: Xu, Mengjia, Rangamani, Akshay, Liao, Qianli, Galanti, Tomer, Poggio, Tomaso
Formato: Online Artículo Texto
Lenguaje:English
Publicado: AAAS 2023
Materias:
Research Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10202460/
https://www.ncbi.nlm.nih.gov/pubmed/37223467
http://dx.doi.org/10.34133/research.0024

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10202460/
https://www.ncbi.nlm.nih.gov/pubmed/37223467
http://dx.doi.org/10.34133/research.0024

Ejemplares similares