Deep classifier neural networks enter the terminal phase of training (TPT) when training
error reaches zero and tend to exhibit intriguing Neural Collapse (NC) properties. Neural …

When training deep neural networks for classification tasks, an intriguing empirical
phenomenon has been widely observed in the last-layer classifiers and features, where (i) …

We provide the first global optimization landscape analysis of Neural Collapse--an intriguing
empirical phenomenon that arises in the last-layer classifiers and features of neural …

A recent study has shown a phenomenon called neural collapse in that the within-class
means of features and the classifier weight vectors converge to the vertices of a simplex …

Modern deep neural networks for classification usually jointly learn a backbone for
representation and a linear classifier to output the logit of each class. A recent study has …

The modern strategy for training deep neural networks for classification tasks includes
optimizing the network's weights even after the training error vanishes to further push the …

While cross entropy (CE) is the most commonly used loss function to train deep neural
networks for classification tasks, many alternative losses have been developed to obtain …

Neural Collapse refers to the remarkable structural properties characterizing the geometry of
class embeddings and classifier weights, found by deep nets when trained beyond zero …

In this paper, we introduce the Layer-Peeled Model, a nonconvex, yet analytically tractable,
optimization program, in a quest to better understand deep neural networks that are trained …

The recently discovered Neural Collapse (NC) phenomenon occurs pervasively in today's
deep net training paradigm of driving cross-entropy (CE) loss towards zero. During NC, last …