Search Results for author:
Found 3 papers, 2 papers with code
Mind the GAP: Improving Robustness to Subpopulation Shifts with Group-Aware Priors
Machine learning models often perform poorly under subpopulation shifts in the data distribution.
Manipulating Sparse Double Descent
This paper investigates the double descent phenomenon in two-layer neural networks, focusing on the role of L1 regularization and representation dimensions.
On the Robustness of Neural Collapse and the Neural Collapse of Robustness
Neural Collapse refers to the curious phenomenon in the end of training of a neural network, where feature vectors and classification weights converge to a very simple geometrical arrangement (a simplex).
Cannot find the paper you are looking for? You can
Submit a new open access paper.
