Two Speeds of Learning: A Representation-Readout Decomposition of Grokking and Double Descent 文章

ArXiv CS.AI2026-05-27NEWSen作者: Chi-Ning Chou, Oscar Uzdelewicz, Neng-Chun Chiu, Yao-Yuan Yang, SueYeon Chung
查看原文 →
关系图谱

Two Speeds of Learning: A Representation-Readout Decomposition of Grokking and Double Descent · 相关技术

相关技术

APISSEORMODEPLAneural networkStanParts-of-Speech (POS) tagsPETICTHISGrokkingForENACamouflaged object detectionAccountsANN