Author name: Ming-Hong Yao, Di Wang, Jian Cui, Jin-Yan Chen, Zi-Hao Cui, Fa Wang, Chen Wei, Qiu-Ye Yu

arXiv:2604.27295v1 Announce Type: cross
Abstract: Learning rate scheduling has evolved from the single global fixed rate of early SGD to sophisticated layer-wise adaptive strategies. We systematize this evolution into five generations: (Gen1) global f…