再论平滑敏感度:迈向最优性
Smooth Sensitivity Revisited: Towards Optimality
AI总结:
针对平滑敏感度差分隐私机制的噪声选择问题,本文提出 PolyPlace 分布,可在标准差上大幅优于 Student's T 分布,并在 $γ\ o0$ 时收敛于 Laplace 机制,从而具有极限最优性。
摘要:
平滑敏感度是设计实用差分隐私机制最常用的技术之一。在该方法中,人们计算给定查询 $q$ 在给定输入 $D$ 上的平滑敏感度,并发布加上与该平滑敏感度成比例的噪声后的 $q(D)$。仍有一个问题:我们应当从什么分布中选取噪声?\n在本文中,我们给出了一类适合与平滑敏感度配合使用的新分布,并将其命名为 PolyPlace 分布。该分布在标准差方面对最先进的 Student's T 分布作出改进,改进倍数可以任意大,具体取决于平滑敏感度框架中必须设置的“平滑度参数” $γ$。此外,我们的分布在更宽的参数 $γ$ 范围内有定义,这可以带来显著更好的性能。\n此外,我们证明 PolyPlace 分布在 $γ\ ightarrow 0$ 时收敛到 Laplace 分布,其方差也同样如此。这意味着 Laplace 机制是 PolyPlace 机制的一个极限特例。这表明我们的机制在某种意义上对于 $γ\ o 0$ 是最优的。
英文摘要:
Smooth sensitivity is one of the most commonly used techniques for designing practical differentially private mechanisms. In this approach, one computes the smooth sensitivity of a given query $q$ on the given input $D$ and releases $q(D)$ with noise added proportional to this smooth sensitivity. One question remains: what distribution should we pick the noise from? In this paper, we give a new class of distributions suitable for the use with smooth sensitivity, which we name the PolyPlace distribution. This distribution improves upon the state-of-the-art Student's T distribution in terms of standard deviation by arbitrarily large factors, depending on a "smoothness parameter" $γ$, which one has to set in the smooth sensitivity framework. Moreover, our distribution is defined for a wider range of parameter $γ$, which can lead to significantly better performance. Moreover, we prove that the PolyPlace distribution converges for $γ\rightarrow 0$ to the Laplace distribution and so does its variance. This means that the Laplace mechanism is a limit special case of the PolyPlace mechanism. This implies that out mechanism is in a certain sense optimal for $γ\to 0$.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。