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

Mengjia Xu, Akshay Rangamani, Qianli Liao, Tomer Galanti, Tomaso Poggio

Research output: Contribution to journalArticlepeer-review

14 Scopus citations

Fingerprint

Dive into the research topics of 'Dynamics in Deep Classifiers Trained with the Square Loss: Normalization, Low Rank, Neural Collapse, and Generalization Bounds'. Together they form a unique fingerprint.

Keyphrases

Mathematics