At critical initialization, the infinite-depth neural tangent kernel converges to the fixed-point output correlation matrix divided by an activation-dependent constant, making learning dynamics equivalent to correlation propagation.
Title resolution pending
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
-
Correlation flow governs learning at criticality
At critical initialization, the infinite-depth neural tangent kernel converges to the fixed-point output correlation matrix divided by an activation-dependent constant, making learning dynamics equivalent to correlation propagation.