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 …

In contrast to batch learning where all training data is available at once, continual learning
represents a family of methods that accumulate knowledge and learn continuously with data …

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 …

When training overparameterized deep networks for classification tasks, it has been widely
observed that the learned features exhibit a so-called" neural collapse'" phenomenon. More …

Many-query problems–arising from, eg, uncertainty quantification, Bayesian inversion,
Bayesian optimal experimental design, and optimization under uncertainty–require …

Current deep learning architectures suffer from catastrophic forgetting, a failure to retain
knowledge of previously learned classes when incrementally trained on new classes. The …

Works have shown the strong connections between some implicit models and optimization
problems. However, explorations on such relationships are limited. Most works pay attention …

Exploring nanoscale material properties through light-matter interactions is essential to
unveil new phenomena and manipulate materials at the atomic level, paving the way for …

Universal approximation capability, also referred to as universality, is an important property
of deep neural networks, endowing them with the potency to accurately represent the …

Distributed machine learning (DML) enables model training on a large corpus of
decentralized data from users and only collects local models or gradients for global …