Clara Na, Sanket Vaibhav Mehta, Emma Strubell. Train Flat, Then Compress: Sharpness-Aware Minimization Learns More Compressible Models. In Yoav Goldberg, Zornitsa Kozareva, Yue Zhang, editors, Findings of the Association for Computational Linguistics: EMNLP 2022, Abu Dhabi, United Arab Emirates, December 7-11, 2022. pages 4909-4936, Association for Computational Linguistics, 2022. [doi]
@inproceedings{NaMS22-1,
title = {Train Flat, Then Compress: Sharpness-Aware Minimization Learns More Compressible Models},
author = {Clara Na and Sanket Vaibhav Mehta and Emma Strubell},
year = {2022},
url = {https://aclanthology.org/2022.findings-emnlp.361},
researchr = {https://researchr.org/publication/NaMS22-1},
cites = {0},
citedby = {0},
pages = {4909-4936},
booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2022, Abu Dhabi, United Arab Emirates, December 7-11, 2022},
editor = {Yoav Goldberg and Zornitsa Kozareva and Yue Zhang},
publisher = {Association for Computational Linguistics},
}