Grokking isn't magic: weight decay contracting spatial oscillations explains generalization

burny_tech · x · 2026-10-01

A technical thread argues that grokking—memorizing the training set long before generalizing—is not explained by flat minima. The author proposes that networks fit training points on a fast timescale, while out-of-sample generalization is a separate, slower process: weight decay gradually contracting spatial oscillations across the input domain. The thread walks through the math behind this claim.

Original post →

More from Research

Research channel →