English

Exploring the Effect of Multi-step Ascent in Sharpness-Aware Minimization

Machine Learning 2023-02-22 v1

Abstract

Recently, Sharpness-Aware Minimization (SAM) has shown state-of-the-art performance by seeking flat minima. To minimize the maximum loss within a neighborhood in the parameter space, SAM uses an ascent step, which perturbs the weights along the direction of gradient ascent with a given radius. While single-step or multi-step can be taken during ascent steps, previous studies have shown that multi-step ascent SAM rarely improves generalization performance. However, this phenomenon is particularly interesting because the multi-step ascent is expected to provide a better approximation of the maximum neighborhood loss. Therefore, in this paper, we analyze the effect of the number of ascent steps and investigate the difference between both single-step ascent SAM and multi-step ascent SAM. We identify the effect of the number of ascent on SAM optimization and reveal that single-step ascent SAM and multi-step ascent SAM exhibit distinct loss landscapes. Based on these observations, we finally suggest a simple modification that can mitigate the inefficiency of multi-step ascent SAM.

Keywords

Cite

@article{arxiv.2302.10181,
  title  = {Exploring the Effect of Multi-step Ascent in Sharpness-Aware Minimization},
  author = {Hoki Kim and Jinseong Park and Yujin Choi and Woojin Lee and Jaewook Lee},
  journal= {arXiv preprint arXiv:2302.10181},
  year   = {2023}
}
R2 v1 2026-06-28T08:44:50.974Z