ENTITY Grokking on the Weight-Decay Clock: A Rate Hierarchy from Softly Broken Symmetries

Grokking on the Weight-Decay Clock: A Rate Hierarchy from Softly Broken Symmetries

PulseAugur coverage of Grokking on the Weight-Decay Clock: A Rate Hierarchy from Softly Broken Symmetries — every cluster mentioning Grokking on the Weight-Decay Clock: A Rate Hierarchy from Softly Broken Symmetries across labs, papers, and developer communities, ranked by signal.

Show in brief

Total · 30d

1 over 90d

Releases · 30d

0 over 90d

Papers · 30d

1 over 90d

TIER MIX · 90D

TOPICS

paper 1
other 1

SENTIMENT · 30D

1 day(s) with sentiment data

RECENT · PAGE 1/1 · 1 TOTAL

TOOL · CL_167256 · Jul 28 · 04:00

New theory explains delayed generalization in AI models

Researchers have identified a mechanism for delayed generalization, known as grokking, in linear models trained with specific optimization techniques and weight decay. Their analysis reveals a 'grokking subspace' within…

New theory explains delayed generalization in AI models