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 2407.11274cs.LGcs.CRstat.ML
收藏

数据与隐私需求相关时的私有估计

Private Estimation when Data and Privacy Demands are Correlated

UC Berkeley, USA(加州大学伯克利分校)

Syomantak Chaudhuri, Thomas A. Courtade

AI总结:

针对数据与隐私需求相关时的私有估计问题,提出算法并在PAC误差和均方误差下建立理论保证,实现极小极大最优,实验验证优于基线。

摘要:

差分隐私(DP)是当前确保统计查询隐私的金标准。文献中在DP约束下的估计问题大多集中于为所有用户提供平等的隐私保护。我们考虑单变量数据的经验均值估计和分类数据的频率估计问题,两者均受异构隐私约束。每个向数据集贡献样本的用户被允许有不同的隐私需求。数据集本身被假定为最坏情况,我们在两种不同的公式下研究这两个问题——第一种,隐私需求和数据可能相关;第二种,通过数据集的随机排列来弱化相关性。我们在PAC误差和均方误差下为所提出的算法建立了理论性能保证。这些性能保证在多种情况下转化为极小极大最优性,实验证实了我们的算法优于其他基线技术的性能。

英文摘要:

Differential Privacy (DP) is the current gold-standard for ensuring privacy for statistical queries. Estimation problems under DP constraints appearing in the literature have largely focused on providing equal privacy to all users. We consider the problems of empirical mean estimation for univariate data and frequency estimation for categorical data, both subject to heterogeneous privacy constraints. Each user, contributing a sample to the dataset, is allowed to have a different privacy demand. The dataset itself is assumed to be worst-case and we study both problems under two different formulations -- first, where privacy demands and data may be correlated, and second, where correlations are weakened by random permutation of the dataset. We establish theoretical performance guarantees for our proposed algorithms, under both PAC error and mean-squared error. These performance guarantees translate to minimax optimality in several instances, and experiments confirm superior performance of our algorithms over other baseline techniques.

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。

↑