Tight Bounds for Gaussian Mean Estimation under Personalized Differential Privacy

2026-01-22

AI Summary

This study investigates the optimal mechanisms for estimating the mean of a Gaussian distribution under personalized differential privacy (PDP), considering both bounded and unbounded PDP settings. In the unbounded PDP regime, where both participation information and individual privacy budgets must be protected, the work proposes a novel weighted estimator that jointly leverages data values and privacy budgets. By establishing minimax lower bounds and designing an algorithm whose error matches these bounds up to logarithmic factors, the paper presents the first unified framework achieving tight upper and lower bounds in both PDP settings. The proposed estimator attains near-optimal performance, with its theoretical error exceeding the minimax lower bound only by a logarithmic factor.

Technology Category

• Machine Learning: Privacy
• Reasoning under Uncertainty: Stochastic Optimization
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems
• Security and Privacy: Privacy-enhancing technologies
• Economics, Online Markets and Human Computation: Fairness, privacy, and diversity in economic environments

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.

Problem

• Gaussian mean estimation
• personalized differential privacy
• unbounded support
• privacy budget
• unbounded PDP

Innovation

• Gaussian mean estimation
• personalized differential privacy
• unbounded PDP
• tight bounds
• privacy-aware weighting