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.
Then, for any η >0, mint1≤t≤t2 f (x(t)) − f ∗ ≤ (η+Cαβ )β 2 if and only if t2 ≥ t1 + R2 αβη
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.