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
(comprising less than 0.1% of the total parameters) in the adversarial step of
SAM outperforms perturbing all of the parameters. This finding generalizes to
different SAM variants and both ResNet (Batch Normalization) and Vision
Transformer (Layer Normalization) architectures. We consider alternative sparse
perturbation approaches and find that these do not achieve similar performance
enhancement at such extreme sparsity levels, showing that this behaviour is
unique to the normalization layers. Although our findings reaffirm the
effectiveness of SAM in improving generalization performance, they cast doubt
on whether this is solely caused by reduced sharpness. The code for our
experiments is publicly available at this https URL

本文研究了对小部分参数进行扰动的 Sharpness-aware minimization (SAM) 的性能，并通过实验结果证明，只操作正规化处理中几乎不占比例的仿射变换参数能比全局扰动得到更好的效果。