.png){kind=icon}
返回
Noise-resistant sharpness-aware minimization in deep learning
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neunet.2024.106829.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Sharpness-aware minimization (SAM) aims to enhance model generalization by minimizing the sharpness of the loss function landscape, leading to a robust model performance. To protect sensitive information and enhance privacy, prevailing approaches add noise to models. However, additive noises would inevitably degrade the generalization and robustness of the model. In this paper, we propose a noise-resistant SAM method, based on a noise-resistant parameter update rule. We analyze the convergence and noise resistance properties of the proposed method under noisy conditions. We elaborate on experimental results with several networks on various benchmark datasets to demonstrate the advantages of the proposed method with respect to model generalization and privacy protection.
Keyword:
Deep neural networks
Sharpness-aware minimization
Noise resistance
期刊
IF:
6.3
论文数:
8.2K
被引数:
3.0W
机构
引用论文
Evaluation of selected models for estimating solar radiation on horizontal surfaces.png)
Solar Energy
Solar EnergyIF0
PREAI
分享收藏Learning a robust foundation model against clean-label data poisoning attacks at downstream tasks学习强大的基础模型，以防止下游任务中的干净标签数据中毒攻击NEURAL NETWORKS
OAAI
NEURAL NETWORKSIF6.3
OAAI分享收藏分享收藏Low-Latency Multiuser Two-Way Wireless Relaying for Spectral and Energy Efficiencies低延迟多用户双向无线中继，实现频谱和能量效率OAAI
OAAI分享收藏
查看更多内容