Privacy and Statistical Risk: Formalisms and Minimax Bounds

Abstract

We explore and compare a variety of definitions for privacy and disclosure limitation in statistical estimation and data analysis, including (approximate) differential privacy, testing-based definitions of privacy, and posterior guarantees on disclosure risk. We give equivalence results between the definitions, shedding light on the relationships between different formalisms for privacy. We also take an inferential perspective, where---building off of these definitions---we provide minimax risk bounds for several estimation problems, including mean estimation, estimation of the support of a distribution, and nonparametric density estimation. These bounds highlight the statistical consequences of different definitions of privacy and provide a second lens for evaluating the advantages and disadvantages of different techniques for disclosure limitation.

arXiv comment29 pages

Cited by in corpus (22)

• Extremal Mechanisms for Local Differential Privacy
• Protection Against Reconstruction and Its Applications in Private Federated Learning
• Private Mean Estimation of Heavy-Tailed Distributions
• Efficient Mean Estimation with Pure Differential Privacy via a Sum-of-Squares Exponential Mechanism
• On-Average KL-Privacy and its equivalence to Generalization for Max-Entropy Mechanisms
• Improved Rates for Differentially Private Stochastic Convex Optimization with Heavy-Tailed Data
• Robust and Differentially Private Mean Estimation
• The Cost of Privacy in Generalized Linear Models: Algorithms and Minimax Lower Bounds
• Covariance-Aware Private Mean Estimation Without Private Covariance Estimation
• Toward Evaluating Re-identification Risks in the Local Privacy Model
• Element Level Differential Privacy: The Right Granularity of Privacy
• Optimal Rates of (Locally) Differentially Private Heavy-tailed Multi-Armed Bandits
• Differential privacy and robust statistics in high dimensions
• A Private and Computationally-Efficient Estimator for Unbounded Gaussians
• Near Instance-Optimality in Differential Privacy
• A Note on Privacy in Constant Function Market Makers
• Adapting to Function Difficulty and Growth Conditions in Private Optimization
• Statistical Inference in the Differential Privacy Model
• Privately Learning Mixtures of Axis-Aligned Gaussians
• Per-instance Differential Privacy
• Learning with User-Level Privacy
• Pointwise adaptive kernel density estimation under local approximate differential privacy