通过填充-置换指纹编码实现差分隐私算法的平滑下界
Smooth Lower Bounds for Differentially Private Algorithms via Padding-and-Permuting Fingerprinting Codes
AI总结:
本文提出基于填充-置换指纹编码的新框架,为满足弱精度要求的差分隐私算法建立平滑样本复杂度下界,并应用于DP平均、k-means聚类和顶部奇异向量估计等问题。
摘要:
指纹论证方法由 Bun、Ullman 和 Vadhan(STOC 2014)首次提出,是建立近似差分隐私(DP)算法样本复杂度或误差下界的最广泛使用的方法。然而,差分隐私中仍有许多问题我们不知道合适的下界,即使对于已知的问题,其下界也不平滑,并且当误差大于某个阈值时通常会变得无效。我们提出了一个新的框架和工具,用于生成满足非常弱精度要求的差分隐私算法样本复杂度的平滑下界。我们通过在多种设置中提供新的下界来说明我们方法的适用性:1. 低精度区域中 DP 平均的紧下界,这特别蕴含了 Nissim、Stemmer 和 Vadhan(PODS 2016)提出的私有 1-聚类问题的下界。2. 近似 k-means 聚类和一般 (k,z)-聚类的 DP 算法加性误差下界,作为乘性误差的函数,对于常数乘法误差是紧的。3. 在低精度区域中 DP 下估计矩阵顶部奇异向量的下界,这是 Singhal 和 Steinke(NeurIPS 2021)研究的 DP 子空间估计的一个特例。我们的主要技术是将填充-置换变换应用于指纹编码。然而,我们不是通过对现有指纹编码(例如 Tardos 编码)的黑盒访问来证明我们的结果,而是开发了一个新的指纹引理,它比 Dwork 等人(FOCS 2015)和 Bun 等人(SODA 2017)的引理更强,并直接从该引理证明我们的下界。特别地,我们的引理给出了一个具有最优速率(最多多对数因子)的更简单的指纹编码构造,这具有独立的研究价值。
英文摘要:
Fingerprinting arguments, first introduced by Bun, Ullman, and Vadhan (STOC 2014), are the most widely used method for establishing lower bounds on the sample complexity or error of approximately differentially private (DP) algorithms. Still, there are many problems in differential privacy for which we don't know suitable lower bounds, and even for problems that we do, the lower bounds are not smooth, and usually become vacuous when the error is larger than some threshold. We present a new framework and tools to generate smooth lower bounds on the sample complexity of differentially private algorithms satisfying very weak accuracy. We illustrate the applicability of our method by providing new lower bounds in various settings: 1. A tight lower bound for DP averaging in the low-accuracy regime, which in particular implies a lower bound for the private 1-cluster problem introduced by Nissim, Stemmer, and Vadhan (PODS 2016). 2. A lower bound on the additive error of DP algorithms for approximate k-means clustering and general (k,z)-clustering, as a function of the multiplicative error, which is tight for a constant multiplication error. 3. A lower bound for estimating the top singular vector of a matrix under DP in low-accuracy regimes, which is a special case of DP subspace estimation studied by Singhal and Steinke (NeurIPS 2021). Our main technique is to apply a padding-and-permuting transformation to a fingerprinting code. However, rather than proving our results using a black-box access to an existing fingerprinting code (e.g., Tardos' code), we develop a new fingerprinting lemma that is stronger than those of Dwork et al. (FOCS 2015) and Bun et al. (SODA 2017), and prove our lower bounds directly from the lemma. Our lemma, in particular, gives a simpler fingerprinting code construction with optimal rate (up to polylogarithmic factors) that is of independent interest.
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。