paper-with-me

홈 › Papers

LightSAM: Parameter-Agnostic Sharpness-Aware Minimization

2025-05-30 · Yifei Cheng, Li Shen, Hao Sun, Nan Yin, Xiaochun Cao, Enhong Chen

Sharpness-Aware Minimization (SAM) optimizer enhances the generalization ability of the machine learning model by exploring the flat minima landscape through weight perturbations. Despite its empirical success, SAM introduces an additional hyper-parameter, the perturbation radius, which causes the sensitivity of SAM to it. Moreover, it has been proved that the perturbation radius and learning rate of SAM are constrained by problem-dependent parameters to guarantee convergence. These limitations indicate the requirement of parameter-tuning in practical applications. In this paper, we propose the algorithm LightSAM which sets the perturbation radius and learning rate of SAM adaptively, thus extending the application scope of SAM. LightSAM employs three popular adaptive optimizers, including AdaGrad-Norm, AdaGrad and Adam, to replace the SGD optimizer for weight perturbation and model updating, reducing sensitivity to parameters. Theoretical results show that under weak assumptions, LightSAM could converge ideally with any choices of perturbation radius and learning rate, thus achieving parameter-agnostic. We conduct preliminary experiments on several deep learning tasks, which together with the theoretical findings validate the the effectiveness of LightSAM.

📄 PDF Abstract BibTeX arXiv:2505.24399

Code (0)

등록된 구현이 없습니다.

Tasks

Sensitivity

Methods 이 논문이 사용한 방법론

SGD Stochastic Gradient Descent is an iterative optimization technique that uses minibatches of data to form an expectation of the gradient, rather than the full gradient using…
AdaGrad AdaGrad is a stochastic optimization method that adapts the learning rate to the parameters. It performs smaller updates for parameters associated with frequently occurring…
SAM 설명 없음
Adam 설명 없음

Similar Papers 제목 키워드 기반

Sharp-MAML: Sharpness-Aware Model-Agnostic Meta Learning

2022-06-08 · Momin Abbas, Quan Xiao, Lisha Chen, Pin-Yu Chen 외

Model-agnostic meta learning (MAML) is currently one of the dominating approaches for few-shot meta-learning. Albeit its effectiveness, the optimization of MAML can be challenging due to the innate bilevel problem struct…

Meta-Learningmodel

TRAM: Bridging Trust Regions and Sharpness Aware Minimization

2023-10-05 · Tom Sherborne, Naomi Saphra, Pradeep Dasigi, Hao Peng

Sharpness-aware minimization (SAM) reports improving domain generalization by reducing the loss surface curvature in the parameter space. However, generalization during fine-tuning is often more dependent on the transfer…

Cross-Lingual TransferDomain GeneralizationLanguage ModelingLanguage Modelling+1

Towards Compact and Robust DNNs via Compression-aware Sharpness Minimization

2026-01-28 · Jialuo He, Huangxun Chen arxiv

Sharpness-Aware Minimization (SAM) has recently emerged as an effective technique for improving DNN robustness to input variations. However, its interplay with the compactness requirements of on-device DNN deployments re…

Sharpness-Aware Hybrid Model Learning for Architecture-Agnostic Parameter Estimation

2026-02-06 · Naoya Takeishi arxiv

Hybrid modeling, the combination of machine learning models and scientific mathematical models, enables flexible and robust data-driven prediction with partial interpretability. However, the unknown parameters of the sci…

Agnostic Sharpness-Aware Minimization

2024-06-11 · Van-Anh Nguyen, Quyen Tran, Tuan Truong, Thanh-Toan Do 외

Sharpness-aware minimization (SAM) has been instrumental in improving deep neural network training by minimizing both the training loss and the sharpness of the loss landscape, leading the model into flatter minima that …

Meta-Learning