arxiv
PublishedJuly 10, 2026 at 4:00 AM
—neutral
A Stochastic--Geometric Theory of Scaling Laws in Grokking
Publisher summary· verbatim
arXiv:2606.30388v3 Announce Type: replace-cross Abstract: Delayed generalization (\ie~grokking) refers to the phenomenon in which a neural network fits its training data early in training but only begins to generalize after a prolonged delay, often through an abrupt transition. Despite extensive emp
Stay posted· Newsletter
A 5-min weekly brief — top movers, price watch, story of the week.
Discussion
No replies yet. Be first.
The Bubble Brief
WEEKLYRead AI insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗