arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2405.18534cs.DScs.CR
收藏

通过子采样实现个性化隐私核算及其在组合优化中的应用

Individualized Privacy Accounting via Subsampling with Applications in Combinatorial Optimization

Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Adam Sealfon

AI总结:

本文提出基于子采样的个性化隐私核算新技术,将单边DP转化为双边DP,从而为组合优化问题(如可分解子模最大化和集合覆盖)及流中移动重击手问题提供纯DP算法,误差渐近紧且优于先前的近似DP方法。

摘要:

在这项工作中,我们通过以下简单观察给出了一种分析个性化隐私核算的新技术:如果算法是单边加法差分隐私(one-sided add-DP),那么其子采样变体满足双边差分隐私(two-sided DP)。由此,我们获得了若干改进的私有组合优化问题算法,包括可分解子模最大化和集合覆盖。我们的误差保证是渐近紧的,且我们的算法满足纯差分隐私(pure-DP),而先前已知算法(Gupta et al., 2010; Chaturvedi et al., 2021)是近似差分隐私(approximate-DP)。我们还展示了该技术在组合优化之外的应用,为流中的移动重击手问题(shifting heavy hitter problem)给出了一种纯差分隐私算法;此前仅已知近似差分隐私算法(Kaplan et al., 2021; Cohen & Lyu, 2023)。

英文摘要:

In this work, we give a new technique for analyzing individualized privacy accounting via the following simple observation: if an algorithm is one-sided add-DP, then its subsampled variant satisfies two-sided DP. From this, we obtain several improved algorithms for private combinatorial optimization problems, including decomposable submodular maximization and set cover. Our error guarantees are asymptotically tight and our algorithm satisfies pure-DP while previously known algorithms (Gupta et al., 2010; Chaturvedi et al., 2021) are approximate-DP. We also show an application of our technique beyond combinatorial optimization by giving a pure-DP algorithm for the shifting heavy hitter problem in a stream; previously, only an approximateDP algorithm was known (Kaplan et al., 2021; Cohen & Lyu, 2023).

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。

↑