arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1802.03441cs.CR
收藏

局部私有假设检验

Locally Private Hypothesis Testing

Or Sheffet

摘要:

我们在标准(对称)随机响应机制(Warner,1965,Kasiviswanathan et al,2008)和较新的(非对称)机制(Basily和Smith,2015,Basily et al,2017)下启动了局部模型中差异私有假设检验的研究。首先,我们研究的一般框架,每个用户的类型映射到一个信号,并表明,在信号的最大似然分布的问题是可行的。然后,我们讨论的随机响应机制,并表明,在本质上,它映射到新的集合,仿射翻译的原始集合的零假设和替代假设。然后,我们给出了随机响应下的身份和独立性测试的样本复杂性界。然后,我们移动到较新的非对称机制,并表明,也有问题的最大似然分布是可行的。在Basily等人(2007)的机制下,我们给出了比对称情况下的测试者具有更好的样本复杂度的身份和独立性测试者,并提出了一个基于$χ^2$的身份测试者,并进行了实证研究。

英文摘要:

We initiate the study of differentially private hypothesis testing in the local-model, under both the standard (symmetric) randomized-response mechanism (Warner, 1965, Kasiviswanathan et al, 2008) and the newer (non-symmetric) mechanisms (Bassily and Smith, 2015, Bassily et al, 2017). First, we study the general framework of mapping each user's type into a signal and show that the problem of finding the maximum-likelihood distribution over the signals is feasible. Then we discuss the randomized-response mechanism and show that, in essence, it maps the null- and alternative-hypotheses onto new sets, an affine translation of the original sets. We then give sample complexity bounds for identity and independence testing under randomized-response. We then move to the newer non-symmetric mechanisms and show that there too the problem of finding the maximum-likelihood distribution is feasible. Under the mechanism of Bassily et al (2007) we give identity and independence testers with better sample complexity than the testers in the symmetric case, and we also propose a $χ^2$-based identity tester which we investigate empirically.

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。

↑