Minimax Optimal Procedures for Locally Private Estimation

DOI10.1080/01621459.2017.1389735zbMath1398.62021arXiv1604.02390OpenAlexW2963881987WikidataQ89896917 ScholiaQ89896917MaRDI QIDQ4690944

John C. Duchi, Martin J. Wainwright, Michael I. Jordan

Publication date: 23 October 2018

Published in: Journal of the American Statistical Association (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1604.02390

zbMATH Keywords

differential privacyminimax boundsoptimal estimators

Mathematics Subject Classification ID

Density estimation (62G07) Nonparametric estimation (62G05) Generalized linear models (logistic models) (62J12) Sampling theory, sample surveys (62D05) Minimax procedures in statistical decision theory (62C20) Sequential statistical analysis (62L10) Statistical aspects of information-theoretic topics (62B10)

Related Items

Private Sequential Learning, On the universal consistency of histograms anonymised by a randomised response technique, Obtaining minimax lower bounds: a review, Local differential privacy: elbow effect in optimal density estimation and adaptation over Besov ellipsoids, Private Sampling: A Noiseless Approach for Generating Differentially Private Synthetic Data, Multivariate density estimation from privatised data: universal consistency and minimax rates, Phase transitions for support recovery under local differential privacy, Minimax randomized response methods for protecting respondent’s privacy, Distribution-invariant differential privacy, Goodness-of-fit testing for Hölder continuous densities under local differential privacy, The right complexity measure in locally private estimation: it is not the Fisher information, Density estimation under local differential privacy and Hellinger loss, Interactive versus noninteractive locally differentially private estimation: two elbows for the quadratic functional, Canonical noise distributions and private hypothesis tests, On robustness and local differential privacy, Differentially private inference via noisy optimization, An information theoretic approach to post randomization methods under differential privacy, A criterion for privacy protection in data collection and its attainment via randomized response procedures, Geometrizing rates of convergence under local differential privacy constraints, Principal component analysis in the local differential privacy model, On density estimation at a fixed point under local differential privacy, Strongly universally consistent nonparametric regression and classification with privatised data, The cost of privacy: optimal rates of convergence for parameter estimation with differential privacy, On the power of multiple anonymous messages: frequency estimation and selection in the shuffle model of differential privacy, Tight lower bound of sparse covariance matrix estimation in the local differential privacy model, Minimax optimal goodness-of-fit testing for densities and multinomials under a local differential privacy constraint, Optimal locally private estimation under \(\ell_p\) loss for \(1\le p\le 2\), Privacy-Preserving Parametric Inference: A Case for Robust Statistics, Topics and Techniques in Distribution Testing: A Biased but Representative Sample

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Statistics for high-dimensional data. Methods, theory and applications.
• High-dimensional regression with noisy and missing data: provable guarantees with nonconvexity
• Nonparametric curve estimation. Methods, theory, and applications
• Information-theoretic determination of minimax rates of convergence
• Convergence of estimates under dimensionality restrictions
• Randomized Response: A Survey Technique for Eliminating Evasive Answer Bias
• On the Fundamental Limits of Adaptive Sensing
• What Can We Learn Privately?
• On optimal and data-based histograms
• Bounds on the Sample Complexity for Private Learning and Private Data Release
• Distributed Private Data Analysis: Simultaneously Solving How and What
• Robust Stochastic Approximation Approach to Stochastic Programming
• Optimal Rates of Convergence for Deconvolving a Density
• Acceleration of Stochastic Approximation by Averaging
• Differential privacy and robust statistics
• A Statistical Framework for Differential Privacy
• Interpretations of Directed Information in Portfolio Theory, Data Compression, and Hypothesis Testing
• Privacy-preserving statistical estimation with optimal convergence rates
• Elements of Information Theory
• Theory of Cryptography
• Introduction to nonparametric estimation
• Inference using noisy degrees: differentially private \(\beta\)-model and synthetic graphs
• A unified framework for high-dimensional analysis of \(M\)-estimators with decomposable regularizers