Sharpness-Aware Minimization Revisited: Weighted Sharpness as a Regularization Term

Yue, Y; Jiang, JD; Ye, ZL; Gao, N; Liu, YC; Zhang, K

Yue, Y (通讯作者),Ant Grp, Hangzhou, Zhejiang, Peoples R China.

PROCEEDINGS OF THE 29TH ACM SIGKDD CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, KDD 2023, 2023; (): 3185

Abstract

Deep Neural Networks (DNNs) generalization is known to be closely related to the flatness of minima, leading to the development of Sharpness-Aware Min......

Full Text Link