ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks
Abstract
Recently, learning algorithms motivated from sharpness of loss surface as an effective measure of generalization gap have shown state-of-the-art performances. Nevertheless, sharpness defined in a rigid region with a fixed radius, has a drawback in sensitivity to parameter re-scaling which leaves the loss unaffected, leading to weakening of the connection between sharpness and generalization gap. In this paper, we introduce the concept of adaptive sharpness which is scale-invariant and propose the corresponding generalization bound. We suggest a novel learning method, adaptive sharpness-aware minimization (ASAM), utilizing the proposed generalization bound. Experimental results in various benchmark datasets show that ASAM contributes to significant improvement of model generalization performance.
Cite
Text
Kwon et al. "ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks." International Conference on Machine Learning, 2021.Markdown
[Kwon et al. "ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks." International Conference on Machine Learning, 2021.](https://mlanthology.org/icml/2021/kwon2021icml-asam/)BibTeX
@inproceedings{kwon2021icml-asam,
title = {{ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks}},
author = {Kwon, Jungmin and Kim, Jeongseop and Park, Hyunseo and Choi, In Kwon},
booktitle = {International Conference on Machine Learning},
year = {2021},
pages = {5905-5914},
volume = {139},
url = {https://mlanthology.org/icml/2021/kwon2021icml-asam/}
}