The right complexity measure in locally private estimation: it is not the Fisher information

DOI10.1214/22-aos2227arXiv1806.05756OpenAlexW2808701946MaRDI QIDQ6151956

John C. Duchi, Feng Ruan

Publication date: 11 March 2024

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

Full work available at URL: https://arxiv.org/abs/1806.05756

zbMATH Keywords

\(L^1\) informationlocal minimax complexitylocally private estimationstrong data processing inequalities

Mathematics Subject Classification ID

Nonparametric hypothesis testing (62G10) Nonparametric estimation (62G05) Privacy of data (68P27)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Asymptotic methods in statistical decision theory
• Estimating a bounded normal mean
• Geometrizing rates of convergence. II
• Geometrizing rates of convergence. III
• Pointwise and sup-norm sharp adaptive estimation of functions on the Sobolev classes
• A constrained risk inequality with applications to nonparametric functional estimation
• On contraction properties of Markov kernels
• Asymptotics in statistics. Some basic concepts.
• Geometrizing rates of convergence under local differential privacy constraints
• The privacy blanket of the shuffle model
• On the f-divergence and singularity of probability measures
• Asymptotic optimality in stochastic optimization
• On the geometry of differential privacy
• Randomized Response: A Survey Technique for Eliminating Evasive Answer Bias
• Rényi Divergence and Kullback-Leibler Divergence
• Concentrated Differential Privacy: Simplifications, Extensions, and Lower Bounds
• The Algorithmic Foundations of Differential Privacy
• A Framework For Estimation Of Convex Functions
• On Divergences and Informations in Statistics and Information Theory
• Graphical Models, Exponential Families, and Variational Inference
• Acceleration of Stochastic Approximation by Averaging
• Respondent Jeopardy and Optimal Designs in Randomized Response Models
• Asymptotic Statistics
• Minimax Optimal Procedures for Locally Private Estimation
• [https://portal.mardi4nfdi.de/wiki/Publication:4743580 Approximation dans les espaces m�triques et th�orie de l'estimation]
• Panning for Gold: ‘Model-X’ Knockoffs for High Dimensional Controlled Variable Selection
• Amplification by Shuffling: From Local to Central Differential Privacy via Anonymity
• A Statistical Framework for Differential Privacy
• Information-Theoretic Lower Bounds on the Oracle Complexity of Stochastic Convex Optimization
• Testing Statistical Hypotheses
• Elements of Information Theory
• Theory of Cryptography
• Introduction to nonparametric estimation

This page was built for publication: The right complexity measure in locally private estimation: it is not the Fisher information