paper-with-me

홈 › Papers

Sharpness-Aware Minimization: General Analysis and Improved Rates

2025-03-04 · Dimitris Oikonomou, Nicolas Loizou

Sharpness-Aware Minimization (SAM) has emerged as a powerful method for improving generalization in machine learning models by minimizing the sharpness of the loss landscape. However, despite its success, several important questions regarding the convergence properties of SAM in non-convex settings are still open, including the benefits of using normalization in the update rule, the dependence of the analysis on the restrictive bounded variance assumption, and the convergence guarantees under different sampling strategies. To address these questions, in this paper, we provide a unified analysis of SAM and its unnormalized variant (USAM) under one single flexible update rule (Unified SAM), and we present convergence results of the new algorithm under a relaxed and more natural assumption on the stochastic noise. Our analysis provides convergence guarantees for SAM under different step size selections for non-convex problems and functions that satisfy the Polyak-Lojasiewicz (PL) condition (a non-convex generalization of strongly convex functions). The proposed theory holds under the arbitrary sampling paradigm, which includes importance sampling as special case, allowing us to analyze variants of SAM that were never explicitly considered in the literature. Experiments validate the theoretical findings and further demonstrate the practical effectiveness of Unified SAM in training deep neural networks for image classification tasks.

📄 PDF Abstract BibTeX arXiv:2503.02225

Code (1)

dimitris-oik/unifiedsam 공식 구현 pytorch

Tasks

image-classificationImage Classification

Methods 이 논문이 사용한 방법론

SAM 설명 없음

Similar Papers 제목 키워드 기반

DGSAM: Domain Generalization via Individual Sharpness-Aware Minimization

2025-03-30 · Youngjun Song, Youngsik Hwang, Jonghun Lee, Heechang Lee 외

Domain generalization (DG) aims to learn models that can generalize well to unseen domains by training only on a set of source domains. Sharpness-Aware Minimization (SAM) has been a popular approach for this, aiming to f…

Computational EfficiencyDomain Generalization

Sharpness-Aware Minimization Revisited: Weighted Sharpness as a Regularization Term

2023-05-25 · Yun Yue, Jiadi Jiang, Zhiling Ye, Ning Gao 외

Deep Neural Networks (DNNs) generalization is known to be closely related to the flatness of minima, leading to the development of Sharpness-Aware Minimization (SAM) for seeking flatter minima and better generalization. …

RSAM: Learning on manifolds with Riemannian Sharpness-aware Minimization

2023-09-29 · Tuan Truong, Hoang-Phi Nguyen, Tung Pham, Minh-Tuan Tran 외

Nowadays, understanding the geometry of the loss landscape shows promise in enhancing a model's generalization ability. In this work, we draw upon prior works that apply geometric principles to optimization and present a…

Contrastive Learningimage-classificationImage Classification

SADT: Combining Sharpness-Aware Minimization with Self-Distillation for Improved Model Generalization

2022-11-01 · Masud An-Nur Islam Fahim, Jani Boutellier

Methods for improving deep neural network training times and model generalizability consist of various data augmentation, regularization, and optimization approaches, which tend to be sensitive to hyperparameter settings…

Data Augmentation

Leveraging Extragradient for Effective Sharpness-Aware Minimization in Deep Learning

2026-07-07 · Yao Fu, Chunxia Zhang, Junmin Liu, Yihang Jin 외 arxiv

Generalization remains a pivotal challenge in deep learning, where traditional optimizers like Stochastic Gradient Descent (SGD) often converge to sharp minima, leading to overfitting and reduced performance on unseen da…