arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2407.04945math.STcs.CRcs.LGstat.TH
收藏

关于差分隐私U统计量

On Differentially Private U Statistics

University of California San Diego(加利福尼亚大学圣迭戈分校);University of Cambridge(剑桥大学);University of Texas at Austin(德克萨斯大学奥斯汀分校)

Kamalika Chaudhuri, Po-Ling Loh, Shourya Pandey, Purnamrita Sarkar

AI总结:

本文研究差分隐私下U统计量的估计问题,提出基于局部Hájek投影的阈值化方法以改进现有私有均值估计算法的次优误差,并在非退化与退化情形下取得近乎最优的私有误差。

摘要:

我们考虑私有估计参数 $\mathbb{E}[h(X_1,\dots,X_k)]$ 的问题,其中 $X_1, X_2, \dots, X_k$ 是来自某分布的独立同分布数据,$h$ 是一个置换不变函数。在没有隐私约束的情况下,标准估计量是U统计量,它们广泛出现在众多问题中,包括非参数符号秩检验、对称性检验、均匀性检验以及随机网络中的子图计数,并且在温和条件下可被证明是最小方差无偏估计量。尽管近期对私有均值估计的兴趣大量涌现,但将U统计量私有化却很少受到关注。虽然现有的私有均值估计算法可以被用来获得置信区间,但我们证明它们可能导致次优的私有误差,例如,在主导项中出现常数因子的膨胀,甚至在退化情形下产生 $\Theta(1/n)$ 而非 $O(1/n^2)$ 的误差。为了解决这一问题,我们提出了一种新的基于阈值化的方法,使用局部Hájek投影来重新加权数据的不同子集。这使得非退化U统计量获得近乎最优的私有误差,并为退化U统计量的近最优性提供了有力证据。

英文摘要:

We consider the problem of privately estimating a parameter $\mathbb{E}[h(X_1,\dots,X_k)]$, where $X_1$, $X_2$, $\dots$, $X_k$ are i.i.d. data from some distribution and $h$ is a permutation-invariant function. Without privacy constraints, standard estimators are U-statistics, which commonly arise in a wide range of problems, including nonparametric signed rank tests, symmetry testing, uniformity testing, and subgraph counts in random networks, and can be shown to be minimum variance unbiased estimators under mild conditions. Despite the recent outpouring of interest in private mean estimation, privatizing U-statistics has received little attention. While existing private mean estimation algorithms can be applied to obtain confidence intervals, we show that they can lead to suboptimal private error, e.g., constant-factor inflation in the leading term, or even $Θ(1/n)$ rather than $O(1/n^2)$ in degenerate settings. To remedy this, we propose a new thresholding-based approach using \emph{local Hájek projections} to reweight different subsets of the data. This leads to nearly optimal private error for non-degenerate U-statistics and a strong indication of near-optimality for degenerate U-statistics.

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。

↑