Instance-optimal Mean Estimation Under Differential Privacy

Instance-optimal Mean Estimation Under Differential Privacy
复制标题

差分隐私下的实例最优均值估计

DOI:
--
复制
发表时间:
2021
期刊:
Neural Information Processing Systems
影响因子:
--
通讯作者:
K. Yi
K. Yi
中科院分区:
--
文献类型:
--
作者:
Ziyue Huang;Yuting Liang;K. Yi

文献摘要

参考文献

被引文献

相似文献

差异隐私下的平均估计是一个基本问题,但是当全球敏感性非常大时,最佳的最佳机制并不能在实践中提供有意义的实用性。取而代之的是,已经提出了各种启发式方法,以减少不类似最坏情况实例的现实世界数据的错误。本文采用了一种原则性的方法,从而产生了一种实例最佳的机制。除了其理论最优性外,该机制也很简单且实用,并且可以适应各种数据特征,而无需参数调整。它也很容易扩展到本地和洗牌模型。
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.
通过近似逆敏感性机制实现差分隐私中的实例最优性
DOI: --
发表时间: 2020
期刊: Advances in neural information processing systems
影响因子: --
作者:
Asi, Hilal;Duchi, John
通讯作者: Duchi, John
DOI: --
发表时间: 2018-05
期刊: --
影响因子: --
作者:
Gautam Kamath;Jerry Li;Vikrant Singhal;Jonathan Ullman
通讯作者: Gautam Kamath;Jerry Li;Vikrant Singhal;Jonathan Ullman
DOI: 10.1016/j.ekir.2018.04.002
发表时间: 2018-04-16
影响因子: 6
作者:
Kume S;Nagasu H;Nangaku M;Nishiyama A;Nakamoto H;Kashihara N
通讯作者: Kashihara N