Tight Bounds for Gaussian Mean Estimation under Personalized Differential Privacy

TL;DR

This paper develops optimal methods for estimating the mean of Gaussian distributions under personalized differential privacy, addressing challenges of unbounded support and privacy profiles, and matching lower bounds up to logarithmic factors.

Contribution

It introduces the first optimal Gaussian mean estimators under both bounded and unbounded personalized differential privacy, with matching lower bounds.

Findings

Derived lower bounds for Gaussian mean estimation under PDP.

Proposed estimators that match these bounds up to logarithmic factors.

Addressed challenges of unbounded support and privacy profile sensitivity.

Abstract

We study mean estimation for Gaussian distributions under \textit{personalized differential privacy} (PDP), where each record has its own privacy budget. PDP is commonly considered in two variants: \textit{bounded} and \textit{unbounded} PDP. In bounded PDP, the privacy budgets are public and neighboring datasets differ by replacing one record. In unbounded PDP, neighboring datasets differ by adding or removing a record; consequently, an algorithm must additionally protect participation information, making both the dataset size and the privacy profile sensitive. Existing works have only studied mean estimation over bounded distributions under bounded PDP. Different from mean estimation for distributions with bounded range, where each element can be treated equally and we only need to consider the privacy diversity of elements, the challenge for Gaussian is that, elements can have very different contributions due to the unbounded support. we need to jointly consider the privacy information and the data values. Such a problem becomes even more challenging under unbounded PDP, where the privacy information is protected and the way to compute the weights becomes unclear. In this paper, we address these challenges by proposing optimal Gaussian mean estimators under both bounded and unbounded PDP, where in each setting we first derive lower bounds for both problems, following PDP mean estimators with the algorithmic upper bounds matching the corresponding lower bounds up to logarithmic factors.