A general random matrix stability theorem shows when sparse or correlated neural-network weights still preserve stable Jacobians, and derives the required weight-rescaling.
Elementary inequalities for Mills’ ratio
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
On the Stability of the Jacobian Matrix in Deep Neural Networks
A general random matrix stability theorem shows when sparse or correlated neural-network weights still preserve stable Jacobians, and derives the required weight-rescaling.