δ-SAM: Sharpness-Aware Minimization with Dynamic Reweighting
Deep neural networks are often overparameterized and may not easily achieve model generalization. Adversarial training has shown effectiveness in improving generalization by regularizing the change of loss on top of adversarially chosen perturbations. The recently proposed sharpness-aware minimization (SAM) algorithm conducts adversarial weight perturbation, encouraging the model to converge to a flat minima. Unfortunately, due to increased computational cost, adversarial weight perturbation can only be efficiently estimated per-batch instead of per-instance by SAM, leading to degraded performance. In this paper, we tackle this efficiency bottleneck and propose the first instance-based weight perturbation method: sharpness-aware minimization with dynamic reweighting (δ-SAM). δ-SAM dynamically reweights perturbation within each batch by estimated guardedness (i.e. unguarded instances are up-weighted), serving as a better approximation to per-instance perturbation. Experiments on various tasks demonstrate the effectiveness of δ-SAM.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Sharpness-Aware Minimization with Dynamic Reweighting
Deep neural networks are often overparameterized and may not easily achieve model generalization. Adversarial training has shown effectiveness in improving generalization by regularizing the change of loss on top of adve…
Natural Language UnderstandingBalanced Sharpness-Aware Minimization for Imbalanced Regression
Regression is fundamental in computer vision and is widely used in various tasks including age estimation, depth estimation, target localization, \etc However, real-world data often exhibits imbalanced distribution, maki…
Depth EstimationAge EstimationImproving Resistance to Noisy Label Fitting by Reweighting Gradient in SAM
Noisy labels pose a substantial challenge in machine learning, often resulting in overfitting and poor generalization. Sharpness-Aware Minimization (SAM), as demonstrated in Foret et al. (2021), improves generalization o…
Understanding Sharpness-Aware Minimization
Sharpness-Aware Minimization (SAM) is a recent training method that relies on worst-case weight perturbations. SAM significantly improves generalization in various settings, however, existing justifications for its succe…
Learning with noisy labelsModel Generalization: A Sharpness Aware Optimization Perspective
Sharpness-Aware Minimization (SAM) and adaptive sharpness-aware minimization (ASAM) aim to improve the model generalization. And in this project, we proposed three experiments to valid their generalization from the sharp…
modelvalid