Improving Sharpness-Aware Minimization with Fisher Mask for Better Generalization on Language Models

Improving Sharpness-Aware Minimization with Fisher Mask for Better Generalization on Language Models Qihuang Zhong author Liang Ding author Li Shen author Peng Mi author Juhua Liu author Bo Du author Dacheng Tao author 2022-12 text Findings of the Association for Computational Linguistics: EMNLP 2022 Yoav Goldberg editor Zornitsa Kozareva editor Yue Zhang editor Association for Computational Linguistics Abu Dhabi, United Arab Emirates conference publication zhong-etal-2022-improving 10.18653/v1/2022.findings-emnlp.300 https://aclanthology.org/2022.findings-emnlp.300/ 2022-12 4064 4085