@article{improvingsharpnessawareminimizationwith, title = {Improving Sharpness-Aware Minimization with Fisher Mask for Better Generalization on Language Models}, author = {Qihuang Zhong and Liang Ding and Li Shen and Peng Mi and Juhua Liu and Bo Du and DaCheng Tao}, year = {2022}, eprint = {2210.05497}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2210.05497v1}, }