论文标题
差异隐私中的近乎实例 - 典型性
Near Instance-Optimality in Differential Privacy
论文作者
论文摘要
我们在差异隐私中开发了两个实例最优性概念，这是受经典统计理论的启发：一种是通过考虑无偏见的机制来定义局部最小风险，另一个是将Cramer-rao结合的类似物，我们表明，利益估算的局部连续性完全决定了这些数量。我们还开发了一种互补的收集机制，我们将其称为逆敏感性机制，这对于大量估计值是实例最佳（或实例最佳）。此外，这些机制在每个实例上都均匀地超过了几个功能类别的平滑灵敏度框架，包括实现的连续功能。我们通过相应的实验仔细地介绍了中位数和稳健回归估计的机制的两个实例。
We develop two notions of instance optimality in differential privacy, inspired by classical statistical theory: one by defining a local minimax risk and the other by considering unbiased mechanisms and analogizing the Cramer-Rao bound, and we show that the local modulus of continuity of the estimand of interest completely determines these quantities. We also develop a complementary collection mechanisms, which we term the inverse sensitivity mechanisms, which are instance optimal (or nearly instance optimal) for a large class of estimands. Moreover, these mechanisms uniformly outperform the smooth sensitivity framework on each instance for several function classes of interest, including real-valued continuous functions. We carefully present two instantiations of the mechanisms for median and robust regression estimation with corresponding experiments.
