sharpness-aware-minimization 13 continual-learning 3 image-classification 2 generalization 2 data-augmentation 2 orthogonal-projection 2 flatness 2 catastrophic-forgetting 2 adversarial-training 2 sophia 1 super-convergence 1 second-order-optimization 1 madgrad 1 lion-optimizer 1 lion 1 weight-decay 1 large-batch-optimization 1 generalization-ability 1 generalization-of-deep-cnn 1 lenet-5 1 mnist 1 deep-learning 1 autoaugment 1 cutmix 1 lr-finder 1 mixup 1 progressive-resizing 1 randaugment 1 sam 1 tensorflow2 1 sharpness 1 understanding-deep-learning 1 dann 1 domain-adaptation 1 icml-2022 1 pytorch 1 flat-minima 1 lifelong-learning 1 pre-training 1 gradient-projection 1 subspace-learning 1 federated-learning 1 personalized-federated-learning 1 deep-neural-networks 1 optimization 1 foundation-models 1 low-rank-adaptation 1 robust-machine-learning- 1 stein-variational-gradient-descent 1 adversarial-attacks 1 black-box-attack 1 distribution-shift 1 gradient-regularization 1 transfer-attack 1 adamw 1 cifar10 1