发帖
雷达卡
ASAM: Adaptive Sharpness-Aware Minimization
for Scale-Invariant Learning of Deep Neural Networks
Jungmin Kwon 1 Jeongseop Kim 1 Hyunseo Park 1 In Kwon Choi 1
Abstract et al., 2021) as a learning algorithm based on PAC-Bayesian
generalization bound, achieves a state-of-the-art generaliza-
Recently, learning algorithms motivated from tion performance for various image classification tasks ben-
sharp ...
京公网安备 11010802022788号
