arXiv cs.AI by Synapse Flow 編集部

Spectral Edge Dynamics: An Analytical-Empirical Study of Phase Transitions in Neural Network Training

概要

arXiv:2603.28964v3 Announce Type: replace-cross Abstract: We develop the spectral edge analysis: phase transitions in neural network training -- grokking, capability gains, loss plateaus -- are controlled by the spectral gap of the rolling-window Gram matrix of parameter updates. In the extreme asp…

元記事を読む →

関連記事