BriefGPT.xyz
Jun, 2020
高维度差分隐私估计器设计
Designing Differentially Private Estimators in High Dimensions
HTML
PDF
Aditya Dhar, Jason Huang
TL;DR
本研究在高维度背景下研究差分隐私的均值估计问题,通过将高维度鲁棒统计的结果应用到差分隐私中,提出了一种计算可行的算法,能够在高维度下完成差分隐私的均值估计,并且在人工合成数据集上表现出了优异的性能。
Abstract
We study differentially private
mean estimation
in a
high-dimensional setting
. Existing
differential privacy
techniques applied to large d
→