arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.00463cs.CRcs.DSstat.ME
收藏

差分隐私下的实例最优均值估计

Instance-optimal Mean Estimation Under Differential Privacy

Ziyue Huang, Yuting Liang, Ke Yi

摘要:

差分隐私下的均值估计是一个基本问题,但当全局敏感度很大时,最坏情况下的最优机制在实践中不能提供有意义的效用保证。相反,已经提出了各种方法来减少不类似于最坏情况实例的真实数据上的错误。本文采取了一种原则性的方法,产生一个机制,是实例优化在很强的意义上。该机制除了具有理论上的最优性外,还具有简单实用、无需参数整定即可适应多种数据特性等优点。它很容易扩展到本地和洗牌模式。

英文摘要:

Mean estimation under differential privacy is a fundamental problem, but worst-case optimal mechanisms do not offer meaningful utility guarantees in practice when the global sensitivity is very large. Instead, various heuristics have been proposed to reduce the error on real-world data that do not resemble the worst-case instance. This paper takes a principled approach, yielding a mechanism that is instance-optimal in a strong sense. In addition to its theoretical optimality, the mechanism is also simple and practical, and adapts to a variety of data characteristics without the need of parameter tuning. It easily extends to the local and shuffle model as well.

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。

↑