论文标题

实例 - 最佳的差异私人估计

Instance-Optimal Differentially Private Estimation

论文作者

McMillan, Audra, Smith, Adam, Ullman, Jon

论文摘要

在这项工作中,我们研究了符合$ε$ - 差异隐私的本地最小收敛估计率。与可能是保守的最差案例速率不同,局部最小值最佳的算法必须适应问题的简单实例。我们为单参数指数族构建本地最小私人估计器,并估算​​分布的尾巴速率。在这些情况下,我们表明了简单假设检验的最佳算法,即Canonne等人最近的最佳私人测试仪。 (2019年),直接告知局部最小值估计算法的设计。

In this work, we study local minimax convergence estimation rates subject to $ε$-differential privacy. Unlike worst-case rates, which may be conservative, algorithms that are locally minimax optimal must adapt to easy instances of the problem. We construct locally minimax differentially private estimators for one-parameter exponential families and estimating the tail rate of a distribution. In these cases, we show that optimal algorithms for simple hypothesis testing, namely the recent optimal private testers of Canonne et al. (2019), directly inform the design of locally minimax estimation algorithms.

扫码加入交流群

加入微信交流群

微信交流群二维码

扫码加入学术交流群,获取更多资源