Grokking delay under cross-entropy is mediated primarily by logit scale and resulting softmax saturation, with weight norm acting only as an upstream handle that adds 1-2% beyond the scale.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.LG 3years
2026 3representative citing papers
Weight decay controls distinct learning regimes in grokking transformers on modular arithmetic, tracked by new cheap attention-based diagnostics with empirical critical value and exponent fits.
Proposes a two-gradient-field model with candidate order parameters alpha_dagger and kappa_c to unify phase transitions across learning theory and non-equilibrium chemistry.
citing papers explorer
-
What Does the Weight Norm Control in Grokking? Logit-Scale Mediation under Cross-Entropy
Grokking delay under cross-entropy is mediated primarily by logit scale and resulting softmax saturation, with weight norm acting only as an upstream handle that adds 1-2% beyond the scale.
-
Weight Decay Regimes in Grokking Transformers: Cheap Online Diagnostics
Weight decay controls distinct learning regimes in grokking transformers on modular arithmetic, tracked by new cheap attention-based diagnostics with empirical critical value and exponent fits.
-
Phase Transitions in Driven Informational Systems: A Two-Field Perspective on Learning Theory and Non-Equilibrium Chemistry
Proposes a two-gradient-field model with candidate order parameters alpha_dagger and kappa_c to unify phase transitions across learning theory and non-equilibrium chemistry.