Interactive versus noninteractive locally differentially private estimation: two elbows for the quadratic functional

DOI10.1214/22-AOS2254arXiv2003.04773OpenAlexW3012252387MaRDI QIDQ6172183

Lukas Steinberger, Cristina Butucea, Angelika Rohde

Publication date: 19 July 2023

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

Full work available at URL: https://arxiv.org/abs/2003.04773

zbMATH Keywords

rate of convergencequadratic functionalminimax estimationnonparametric estimationlocal differential privacy

Mathematics Subject Classification ID

Nonparametric hypothesis testing (62G10) Nonparametric estimation (62G05) Minimax procedures in statistical decision theory (62C20)

Related Items (2)

Phase transitions for support recovery under local differential privacy ⋮ Efficiency in local differential privacy

Cites Work

• Unnamed Item
• Unnamed Item
• Achieving information bounds in non and semiparametric models
• Minimax quadratic estimation of a quadratic functional
• Nonquadratic estimators of a quadratic functional
• Sharp adaptive estimation of quadratic functionals
• Optimal adaptive estimation of a quadratic functional
• Wavelets, approximation, and statistical applications
• Adaptive estimation of a quadratic functional by model selection.
• Estimation of integral functionals of a density
• Decoupling inequalities for the tail probabilities of multivariate \(U\)- statistics
• Minimax estimation of linear and quadratic functionals on sparsity classes
• The cost of privacy: optimal rates of convergence for parameter estimation with differential privacy
• Minimax optimal goodness-of-fit testing for densities and multinomials under a local differential privacy constraint
• Local differential privacy: elbow effect in optimal density estimation and adaptation over Besov ellipsoids
• Geometrizing rates of convergence under local differential privacy constraints
• Goodness-of-fit testing and quadratic functional estimation from indirect observations
• Randomized Response: A Survey Technique for Eliminating Evasive Answer Bias
• What Can We Learn Privately?
• Mathematical Foundations of Infinite-Dimensional Statistical Models
• Compression of Wavelet Decompositions
• Adaptive estimation of a quadratic functional of a density by model selection
• Minimax Optimal Procedures for Locally Private Estimation
• Exponential Separations in Local Differential Privacy
• A Statistical Framework for Differential Privacy
• Privacy-preserving statistical estimation with optimal convergence rates
• Theory of Cryptography

This page was built for publication: Interactive versus noninteractive locally differentially private estimation: two elbows for the quadratic functional