In the study of stochastic systems, the committor function describes the probability that a
system starting from an initial configuration x will reach a set B before a set A. This paper …

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 …

Neural networks trained to solve modular arithmetic tasks exhibit grokking, a phenomenon
where the test accuracy starts improving long after the model achieves 100% training …

Deep neural networks (DNNs) exhibit a surprising structure in their final layer known as
neural collapse (NC), and a growing body of works has currently investigated the …

The Gauss-Newton (GN) matrix plays an important role in machine learning, most evident in
its use as a preconditioning matrix for a wide family of popular adaptive methods to speed …

Deep neural networks (DNNs) exhibit a surprising structure in their final layer known as
neural collapse (NC), and a growing body of works has currently investigated the …

While overparameterization in machine learning models offers great benefits in terms of
optimization and generalization, it also leads to increased computational requirements as …

Modern deep neural networks have been observed to exhibit a simple structure in their final
layer features and weights, commonly referred to as neural collapse. This phenomenon has …

Neural Collapse is a phenomenon where the last-layer representations of a well-trained
neural network converge to a highly structured geometry. In this paper, we focus on its first …

The spurious correlation between the background features of the image and its label arises
due to that the samples labeled with the same class in the training set often co-occurs with a …