Sharpness-Aware Minimization

Also known as SAM

Overview

Sharpness-Aware Minimization studies how to train models that are less sensitive to small changes in their parameters, often by taking a gradient step at a nearby high-loss point. Its variants adapt the perturbation radius or direction, use curvature and blockwise information, or reduce the extra computation; researchers also apply these ideas to federated learning, fine-tuning, and long-tailed data. Theory analyzes convergence and stability, while evaluations commonly measure accuracy, corruption robustness, calibration, and performance across domains. A central tension is that flatter minima do not always guarantee better generalization, and the extra optimization cost and sensitivity to perturbation choices remain practical concerns.

Latest papers

CardsList

41 papers4 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

  1. ZO-SAM: Zero-Order Sharpness-Aware Minimization for Efficient Sparse Training

    Mar 13, 2026Jie Ji, Gen Li, Kaiyuan Deng +2Sharpness-Aware MinimizationSparse Neural Networks

  2. Taming the Long Tail: Efficient Item-wise Sharpness-Aware Minimization for LLM-based Recommender Systems

    Mar 13, 2026Jiaming Zhang, Yuyuan Li, Xiaohua Feng +4Long-Tail RecommendationRecommender Systems

  3. Minor First, Major Last: A Depth-Induced Implicit Bias of Sharpness-Aware Minimization

    Mar 9, 2026Chaewon Moon, Dongkuk Si, Chulhee YunSharpness-Aware MinimizationImplicit Bias

  4. Revisiting Sharpness-Aware Minimization: A More Faithful and Effective Implementation

    Mar 9, 2026Jianlong Chen, Zhiming ZhouSharpness-Aware MinimizationDeep Learning Optimization

  5. FedNSAM:Consistency of Local and Global Flatness for Federated Learning

    Feb 27, 2026Junkang Liu, Fanhua Shang, Yuxuan Tian +2Federated LearningSharpness-Aware Minimization

  6. Towards Understanding The Calibration Benefits of Sharpness-Aware Minimization

    May 29, 2025Chengli Tan, Yubo Zhou, Haishan Ye +7Sharpness-Aware MinimizationModel Calibration

  7. Bilateral Sharpness-Aware Minimization for Flatter Minima

    Sep 20, 2024Jiaxin Deng, Junbiao Pang, Baochang Zhang +1Sharpness-Aware MinimizationNeural Network Generalization