A Systematic Empirical Study of Grokking: Depth, Architecture, Activation, and Regularization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Manir, Shalima Binta, Rupa, Anamika Paul
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2603.25009