Sharpness-Aware Minimization Efficiently Selects Flatter Minima Late In Training

Open Webpage

Zhanpeng Zhou, Mingze Wang, Yuchen Mao, Bingrui Li, Junchi Yan

Published: 01 Jan 2025, Last Modified: 17 May 2025ICLR 2025EveryoneRevisionsBibTeXCC BY-SA 4.0