paper-with-me

홈 › Papers

Attributing Data for Sharpness-Aware Minimization

2025-07-05 · Chenyang Ren, Yifan Jia, Huanyi Xie, Zhaobin Xu, Tianxing Wei, Liangyu Wang, Lijie Hu, Di Wang arxiv

Sharpness-aware Minimization (SAM) improves generalization in large-scale model training by linking loss landscape geometry to generalization. However, challenges such as mislabeled noisy data and privacy concerns have emerged as significant issues. Data attribution, which identifies the contributions of specific training samples, offers a promising solution. However, directly rendering existing data influence evaluation tools such as influence functions (IF) to SAM will be inapplicable or inaccurate as SAM utilizes an inner loop to find model perturbations that maximize loss, which the outer loop then minimizes, resulting in a doubled computational structure. Additionally, this bilevel structure complicates the modeling of data influence on the parameters. In this paper, based on the IF, we develop two innovative data valuation methods for SAM, each offering unique benefits in different scenarios: the Hessian-based IF and the Gradient Trajectory-based IF. The first one provides a comprehensive estimation of data influence using a closed-form measure that relies only on the trained model weights. In contrast, the other IF for SAM utilizes gradient trajectory information during training for more accurate and efficient data assessment. Extensive experiments demonstrate their effectiveness in data evaluation and parameter tuning, with applications in identifying mislabeled data, model editing, and enhancing interpretability.

📄 PDF Abstract BibTeX arXiv:2507.04059

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Model Generalization: A Sharpness Aware Optimization Perspective

2022-08-14 · Jozef Marus Coldenhoff, Chengkun Li, Yurui Zhu

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

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

SAMSON: Sharpness-Aware Minimization Scaled by Outlier Normalization for Improving DNN Generalization and Robustness

2022-11-18 · Gonçalo Mordido, Sébastien Henwood, Sarath Chandar, François Leduc-Primeau

Energy-efficient deep neural network (DNN) accelerators are prone to non-idealities that degrade DNN performance at inference time. To mitigate such degradation, existing methods typically add perturbations to the DNN we…

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

LSAM: Asynchronous Distributed Training with Landscape-Smoothed Sharpness-Aware Minimization

2025-09-03 · Yunfei Teng, Sixin Zhang arxiv

While Sharpness-Aware Minimization (SAM) improves generalization in deep neural networks by minimizing both loss and sharpness, it suffers from inefficiency in distributed large-batch training. We present Landscape-Smoot…