Search Results for author:
Found 5 papers, 1 papers with code
Supervised Contrastive Representation Learning: Landscape Analysis with Unconstrained Features
Recent findings reveal that over-parameterized deep neural networks, trained beyond zero training-error, exhibit a distinctive structural pattern at the final layer, termed as Neural-collapse (NC).
Symmetric Neural-Collapse Representations with Supervised Contrastive Loss: The Impact of ReLU and Batching
Supervised contrastive loss (SCL) is a competitive and often superior alternative to the cross-entropy loss for classification.
On the Implicit Geometry of Cross-Entropy Parameterizations for Label-Imbalanced Data
Aiming to extend this theory to non-linear models, we investigate the implicit geometry of classifiers and embeddings that are learned by different CE parameterizations.
Imbalance Trouble: Revisiting Neural-Collapse Geometry
However, we caution that convergence worsens with increasing imbalances.
On how to avoid exacerbating spurious correlations when models are overparameterized
Overparameterized models fail to generalize well in the presence of data imbalance even when combined with traditional techniques for mitigating imbalances.
