We present an asymptotically optimal $(\epsilon,\delta)$ differentially private mechanism for answering multiple, adaptively asked, $\Delta$-sensitive queries, settling the conjecture of Steinke and Ullman [2020]. Our algorithm has a significant advantage that it adds independent bounded noise to each query, thus providing an absolute error bound. Additionally, we apply our algorithm in adaptive data analysis, obtaining an improved guarantee for answering multiple queries regarding some underlying distribution using a finite sample. Numerical computations show that the bounded-noise mechanism outperforms the Gaussian mechanism in many standard settings.
翻译:我们提出了一个非现时最佳的美元( epsilon,\delta) $( delta) 的私人机制, 用于回答多个适应性要求的敏感查询, 解决Steinke 和 Ullman [ 2020] 的猜想。 我们的算法有很大的优势, 它为每个查询添加了独立的闭锁噪音, 从而提供了绝对的错误。 此外, 我们在适应性数据分析中应用了我们的算法, 在使用有限的样本回答关于某些基本分布的多个问题时获得了更好的保证。 数字计算表明, 约束性噪音机制在许多标准环境中都超过了高斯的机制 。