Neural collapse (NC) refers to the surprising structure of the last layer of deep neural
networks in the terminal phase of gradient descent training. Recently, an increasing amount …

As model size continues to grow and access to labeled training data remains limited,
transfer learning has become a popular approach in many scientific and engineering fields …

Over the past decade, deep learning has proven to be a highly effective tool for learning
meaningful features from raw data. However, it remains an open question how deep …

We study deep neural networks for the multi-label classification (MLab) task through the lens
of neural collapse (NC). Previous works have been restricted to the multi-class classification …

Deep Neural Collapse (DNC) refers to the surprisingly rigid structure of the data
representations in the final layers of Deep Neural Networks (DNNs). Though the …

Over the past few years, an extensively studied phenomenon in training deep networks is
the implicit bias of gradient descent towards parsimonious solutions. In this work, we …

Neural collapse ($\mathcal {NC} $) is a phenomenon observed in classification tasks where
top-layer representations collapse into their class means, which become equinorm …

The ResNet architecture has been widely adopted in deep learning due to its significant
boost to performance through the use of simple skip connections, yet the underlying …

The maximal coding rate reduction (MCR $^ 2$) objective for learning structured and
compact deep representations is drawing increasing attention, especially after its recent …

Deep neural networks (DNNs) at convergence consistently represent the training data in the
last layer via a highly symmetric geometric structure referred to as neural collapse. This …