Dara Bahri, Hossein Mobahi, Yi Tay. Sharpness-Aware Minimization Improves Language Model Generalization. In Smaranda Muresan, Preslav Nakov, Aline Villavicencio, editors, Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2022, Dublin, Ireland, May 22-27, 2022. pages 7360-7371, Association for Computational Linguistics, 2022. [doi]
@inproceedings{BahriMT22, title = {Sharpness-Aware Minimization Improves Language Model Generalization}, author = {Dara Bahri and Hossein Mobahi and Yi Tay}, year = {2022}, url = {https://aclanthology.org/2022.acl-long.508}, researchr = {https://researchr.org/publication/BahriMT22}, cites = {0}, citedby = {0}, pages = {7360-7371}, booktitle = {Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2022, Dublin, Ireland, May 22-27, 2022}, editor = {Smaranda Muresan and Preslav Nakov and Aline Villavicencio}, publisher = {Association for Computational Linguistics}, isbn = {978-1-955917-21-6}, }