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 ...