Layer-Wise Adaptive Gradient Norm Penalizing Method for Efficient and Accurate Deep Learning

Sunwoo Lee

KDD, 2024

arXiv
DOI

This study proposes a computation-efficient model perturbation for accurate deep learning.

BibTeX

@inproceedings{lee2024layer,
  title={Layer-wise adaptive gradient norm penalizing method for efficient and accurate deep learning},
  author={Lee, Sunwoo},
  booktitle={Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining},
  pages={1518--1529},
  year={2024}
}