Sharpness-Aware Minimization and Muon: Robustness under the Spectral Norm
By Wenzhi Zhong · Paper · cs.LG
Sharpness-Aware Minimization (SAM) aims to improve generalization by encouraging insensitivity to small, worst-case parameter perturbations. However, the notion of a "small" perturbation is inherently geometry-dependent: while existing SAM variants have explored a wide range of c