Tag
This paper proposes ReNC, a method for open-world test-time adaptation that leverages neural collapse as a structural prior to filter out-of-distribution samples and refine prototypes for reliable model adaptation.
This paper presents an audited protocol using orthogonal Procrustes alignment to detect donor-specific functional fingerprints in neural networks after Neural Collapse, demonstrating that distinct functional variations remain distinguishable even after convergence on MNIST with MLP-5 networks.
This paper argues that within-class variance in language model representations is not incomplete neural collapse but allocated information storage, and that the allocation obeys an information floor law. Across 14 models, macro-category structure carries only 4–12% of representational variance, while within-token context dominates at 79–91%.
This paper investigates how class label encoding influences neural collapse in neural network classifiers, showing that with one-hot encoding and balanced data, uncentered mean features transition from a simplex equiangular tight frame to an orthogonal frame as bias regularization increases.
This paper studies how depth alone induces an implicit low-rank bias in deep unconstrained feature models trained without regularization, shifting the optimal solution from neural collapse to softmax codes, and provides the first asymptotic and dynamic characterization of this bias under gradient descent with cross-entropy loss.
This paper shows that cross-entropy and supervised contrastive learning are both forms of prototype learning on the hypersphere and proposes normalized losses (NTCE and NONL) that achieve Neural Collapse by design, outperforming standard methods.