1st-Order Magic: Analysis of Sharpness-Aware Minimization
Not on the map. Why?
Abstract (arXiv)
Sharpness-Aware Minimization (SAM) is an optimization technique designed to improve generalization by favoring flatter loss minima. To achieve this, SAM optimizes a modified objective that penalizes sharpness, using computationally efficient approximations. Interestingly, we find that more precise approximations of the proposed SAM objective degrade generalization performance, suggesting that the generalization benefits of SAM are rooted in these approximations rather than in the original intended mechanism. This highlights a gap in our understanding of SAM's effectiveness and calls for further investigation into the role of approximations in optimization.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 8 of its 11 references that are in the map. First posted on arXiv 3 Nov 2024.
Builds on
8 of 11 references.
References · 8
- 2020Sharpness-Aware Minimization for Efficiently Improving Generalizationcited by 1,417
- 2016On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minimacited by 1,352
- 2017Exploring Generalization in Deep Learningcited by 600
- 2017Sharp Minima Can Generalize For Deep Netscited by 466
- 2021ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networkscited by 293
- 2022Understanding Gradient Descent on Edge of Stability in Deep Learningcited by 128
- 2020Regularizing Neural Networks via Adversarial Model Perturbationcited by 78
- 2023Exploring the Effect of Multi-step Ascent in Sharpness-Aware Minimizationcited by 9
Built on by
Not cited yet.