Dynamic Momentum Recalibration in Online Gradient Learning
arXiv:2603.06120v1 Announce Type: new Abstract: Stochastic Gradient Descent (SGD) and its momentum variants form the backbone of deep learning optimization, yet the underlying dynamics of …
Zhipeng Yao, Rui Yu, Guisong Chang, Ying Li, Yu Zhang, Dazhou Li
조회수 34회