Observable Matrix Dynamics (OMD) is a new diagnostic framework that uses random matrix theory on distance matrices to distinguish diffusive relaxations from phase-transition-like reorganizations during neural network training.
arXiv preprint arXiv:2011.11619 , year =
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.LG 3verdicts
UNVERDICTED 3representative citing papers
Supervised classification reaches neural collapse by design via normalized prototype losses on the hypersphere, outperforming CE and SCL on ImageNet-1K and other benchmarks with faster convergence and better transfer.
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.
citing papers explorer
-
Learning as Observable Matrix Dynamics: Diffusive Relaxations versus Phase Transitions
Observable Matrix Dynamics (OMD) is a new diagnostic framework that uses random matrix theory on distance matrices to distinguish diffusive relaxations from phase-transition-like reorganizations during neural network training.
-
Neural Collapse by Design: Learning Class Prototypes on the Hypersphere
Supervised classification reaches neural collapse by design via normalized prototype losses on the hypersphere, outperforming CE and SCL on ImageNet-1K and other benchmarks with faster convergence and better transfer.
-
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.