BriefGPT.xyz
Oct, 2024
用户级局部差分隐私下的分布感知均值估计
Distribution-Aware Mean Estimation under User-level Local Differential Privacy
HTML
PDF
Corentin Pla, Hugo Richard, Maxime Vono
TL;DR
本研究解决了在用户级局部差分隐私下的均值估计问题,特别是在用户数据样本数量不一致的情况下。提出了一种分布感知的均值估计算法,并确定了该算法在最坏情况下的风险界限,结果在对数因素上渐近匹配,并在样本数量相同的情况下收敛到已知界限。这项工作为优化隐私保护下的均值估计提供了新的理论基础。
Abstract
We consider the problem of
Mean Estimation
under user-level
Local Differential Privacy
, where $n$ users are contributing through their local pool of data samples. Previous work assume that the number of data samp
→