The cost of privacy: optimal rates of convergence for parameter estimation with differential privacy

DOI10.1214/21-AOS2058zbMath1486.62074arXiv1902.04495OpenAlexW3211357969MaRDI QIDQ2054532

Linjun Zhang, Yichen Wang, T. Tony Cai

Publication date: 3 December 2021

Published in: The Annals of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1902.04495

zbMATH Keywords

high-dimensional datalinear regressiondifferential privacyminimax optimalitymean estimation

Mathematics Subject Classification ID

Asymptotic properties of parametric estimators (62F12) Linear regression; mixed models (62J05) Parametric inference under constraints (62F30) Minimax procedures in statistical decision theory (62C20) Authentication, digital signatures and secret sharing (94A62)

Related Items

Private Sampling: A Noiseless Approach for Generating Differentially Private Synthetic Data, Interactive versus noninteractive locally differentially private estimation: two elbows for the quadratic functional, On robustness and local differential privacy, Differentially private inference via noisy optimization

Uses Software

• RAPPOR

Cites Work

• Unnamed Item
• Unnamed Item
• Iterative hard thresholding for compressed sensing
• Fast global convergence of gradient methods for high-dimensional statistical recovery
• Statistical estimation and optimal recovery
• On minimax estimation of a sparse normal mean vector
• Sparse spatial autoregressions
• Geometrizing rates of convergence under local differential privacy constraints
• What Can We Learn Privately?
• The Algorithmic Foundations of Differential Privacy
• High-Dimensional Statistics
• Minimax Optimal Procedures for Locally Private Estimation
• Finite Sample Differentially Private Confidence Intervals
• A Statistical Framework for Differential Privacy
• Fingerprinting codes and the price of approximate differential privacy
• Analyze gauss
• Privacy-preserving statistical estimation with optimal convergence rates
• Regularized M-estimators with nonconvexity: Statistical and algorithmic theory for local optima
• Theory of Cryptography
• A unified framework for high-dimensional analysis of \(M\)-estimators with decomposable regularizers