Transformers using elementwise tanh-like nonlinearities instead of LayerNorm show stretched-exponential APJN growth at large depth, indicating subcritical signal propagation unlike the power-law growth in pre-LayerNorm designs.
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
UNVERDICTED 1representative citing papers
citing papers explorer
-
Subcritical Signal Propagation at Initialization in Normalization-Free Transformers
Transformers using elementwise tanh-like nonlinearities instead of LayerNorm show stretched-exponential APJN growth at large depth, indicating subcritical signal propagation unlike the power-law growth in pre-LayerNorm designs.