Numerical vector aggregation plays a crucial role in privacy-sensitive applications, such as distributed gradient estimation in federated learning and statistical analysis of key-value data. In the context of local differential privacy, this study provides a tight minimax error bound of $O(\frac{ds}{n\epsilon^2})$, where $d$ represents the dimension of the numerical vector and $s$ denotes the number of non-zero entries. By converting the conditional/unconditional numerical mean estimation problem into a frequency estimation problem, we develop an optimal and efficient mechanism called Collision. In contrast, existing methods exhibit sub-optimal error rates of $O(\frac{d^2}{n\epsilon^2})$ or $O(\frac{ds^2}{n\epsilon^2})$. Specifically, for unconditional mean estimation, we leverage the negative correlation between two frequencies in each dimension and propose the CoCo mechanism, which further reduces estimation errors for mean values compared to Collision. Moreover, to surpass the error barrier in local privacy, we examine privacy amplification in the shuffle model for the proposed mechanisms and derive precisely tight amplification bounds. Our experiments validate and compare our mechanisms with existing approaches, demonstrating significant error reductions for frequency estimation and mean estimation on numerical vectors.
翻译:数值向量聚合在隐私敏感的应用中扮演着关键角色,例如联邦学习中的分布式梯度估计和键值数据的统计分析。在本地差分隐私的背景下,本文提供了$O(\frac{ds}{n\epsilon^2})$的紧密极小值误差界,其中$d$表示数值向量的维度,$s$表示非零条目的数量。通过将条件/非条件数值均值估计问题转换为频率估计问题,我们开发了一种名为Collision的最优且有效的机制。与现有方法相比,该方法表现出$O(\frac{d^2}{n\epsilon^2})$或$O(\frac{ds^2}{n\epsilon^2})$的次优误差率。具体而言,为了非条件均值估计,我们利用了每个维度中两个频率之间的负相关性,并提出了CoCo机制,相对于Collision进一步减少了均值值的估计误差。此外,为了突破本地隐私中的误差障碍,我们研究了所提出机制在混洗模型中的隐私放大,并得出了精确的放大界限。我们的实验验证并比较了我们的方法与现有方法,证明了在数值向量上进行频率估计和均值估计方面的显着误差减少。