Tiffany Joyce Vlaar

Normalization Layers Are All That Sharpness-Aware Minimization Needs

Sharpness-aware minimization (SAM) was proposed to reduce sharpness of minima and has been shown to enhance generalization performance in various settings. In this work we show that perturbing only the affine normalization parameters (typically comprising 0.1% of the total parameters) in the adversa…