Neural regression collapse occurs when last-layer feature intrinsic dimension falls below target intrinsic dimension, creating over-compressed and under-compressed regimes that govern generalization based on data quantity and noise.
Neural collapse with unconstrained features.arXiv preprint arXiv:2011.11619,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Geometric Analysis of Neural Regression Collapse via Intrinsic Dimension
Neural regression collapse occurs when last-layer feature intrinsic dimension falls below target intrinsic dimension, creating over-compressed and under-compressed regimes that govern generalization based on data quantity and noise.