For the L-layer unconstrained feature model with bias and squared-error loss, the global minimizer's geometric structure is governed by the singular values of the matrix (I - n1^T/N)diag(√n).
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
The Exploration of Neural Collapse under Imbalanced Data
For the L-layer unconstrained feature model with bias and squared-error loss, the global minimizer's geometric structure is governed by the singular values of the matrix (I - n1^T/N)diag(√n).