VIDEO DOI: https://doi.org/10.48448/54g5-6w32

findings / work in progress

EMNLP 2022

Abu Dhabi, United Arab Emirates

Train Flat, Then Compress: Sharpness-Aware Minimization Learns More Compressible Models

Please log in to leave a comment

Downloads

SlidesTranscript English (automatic)

Next from EMNLP 2022

findings / work in progress

Improving Generalization of Pre-trained Language Models via Stochastic Weight Averaging

EMNLP 2022

Peng Lu

Stay up to date with the latest Underline news!

PRESENTATIONS

  • All Lectures
  • For Librarians
  • Resource Center
  • Free Trial
Underline Science, Inc.
1216 Broadway, 2nd Floor, New York, NY 10001, USA

© 2023 Underline - All rights reserved