Grokking is induced by any small nonzero regularizer whose favored solutions generalize, with a delay that scales like one over the learning rate times the regularization strength.
Title resolution pending
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
-
Grokking Beyond the Euclidean Norm of Model Parameters
Grokking is induced by any small nonzero regularizer whose favored solutions generalize, with a delay that scales like one over the learning rate times the regularization strength.