Derives layer-wise recursions for finite-width tensors under orthogonal initialization that reproduce the observed large-depth stability of nonlinear networks.
Feature Learning and Generalization in Deep Networks with Orthogonal Weights
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Criticality and Saturation in Orthogonal Neural Networks
Derives layer-wise recursions for finite-width tensors under orthogonal initialization that reproduce the observed large-depth stability of nonlinear networks.