BriefGPT.xyz
Oct, 2023
带权重剪枝的DP-SGD
DP-SGD with weight clipping
HTML
PDF
Antoine Barczewski, Jan Ramon
TL;DR
通过利用当前全局模型及其在搜索域中的位置的公共信息，我们提出了一种新方法来缓解传统梯度剪裁带来的偏差，从而实现了改进的梯度界限，进一步确定了灵敏度并调整了噪声水平，提供更好的差异性隐私保证，并进行了实证评估。
Abstract
Recently, due to the popularity of
deep neural networks
and other methods whose training typically relies on the optimization of an objective function, and due to concerns for data privacy, there is a lot of interest in
→