The complexity dynamics of grokking

We demonstrate the existence of a complexity phase transition in neural networks by studying the grokking phenomenon, where networks suddenly transition from memorization to generalization long after overfitting their training data. To characterize this phase transition, we introduce a theoretical f...

Full description

Bibliographic Details

Published in:	Physica. D Vol. 482; p. 134859
Main Authors:	DeMoss, Branton, Sapora, Silvia, Foerster, Jakob, Hawes, Nick, Posner, Ingmar
Format:	Journal Article
Language:	English
Published:	Elsevier B.V 01.11.2025
Subjects:	Algorithmic complexity Grokking Phase transition Algorithmic complexity Grokking Phase transition
ISSN:	0167-2789
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!