Strongly universally consistent nonparametric regression and classification with privatised data

DOI10.1214/21-EJS1845zbMath1471.62321arXiv2011.00216MaRDI QIDQ2044383

Thomas B. Berrett, László Györfi, Harro Walk

Publication date: 9 August 2021

Published in: Electronic Journal of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2011.00216

zbMATH Keywords

classificationuniversal consistencyregression estimatelocal differential privacy

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Asymptotic properties of nonparametric inference (62G20) Classification and discrimination; cluster analysis (statistical aspects) (62H30) Privacy of data (68P27)

Related Items (3)

Multivariate density estimation from privatised data: universal consistency and minimax rates ⋮ Density estimation under local differential privacy and Hellinger loss ⋮ On robustness and local differential privacy

Uses Software

• RAPPOR

Cites Work

• Unnamed Item
• Fast learning rates for plug-in classifiers
• RAPPOR
• Adaptive model selection using empirical complexities
• A nearest neighbor estimate of the residual variance
• A distribution-free theory of nonparametric regression
• Local differential privacy: elbow effect in optimal density estimation and adaptation over Besov ellipsoids
• Local nearest neighbour classification with applications to semi-supervised learning
• Geometrizing rates of convergence under local differential privacy constraints
• Extremal Mechanisms for Local Differential Privacy
• Randomized Response: A Survey Technique for Eliminating Evasive Answer Bias
• On the Rate of Convergence of Local Averaging Plug-In Classification Rules Under a Margin Condition
• Minimax Optimal Procedures for Locally Private Estimation
• k-ANONYMITY: A MODEL FOR PROTECTING PRIVACY
• A Statistical Framework for Differential Privacy
• Non-Parametric Estimation II. Statistically Equivalent Blocks and Tolerance Regions--The Continuous Case
• Theory of Cryptography

This page was built for publication: Strongly universally consistent nonparametric regression and classification with privatised data