Versatile differentially private learning for general loss functions

DOI10.1214/25-AOS2583MaRDI QIDQ7227000zbMATH OpenFDO

Authors Qilong Lu, Song Xi Chen, Yumou Qiu

Publication date 8 April 2026

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

Full work available at URL https://projecteuclid.org/journals/annals-of-statistics/volume-54/issue-2/Versatile-differentially-private-learning-for-general-loss-functions/10.1214/25-AOS2583.full

zbMATH Keywords

M-estimationdifferential privacysymmetric multivariate Laplace distributionzero-inflated symmetric multivariate Laplace distribution

Mathematics Subject Classification ID

Research data for problems pertaining to statistics (62-11) Privacy of data (68P27)

Cites work

• scientific article; zbMATH DE number 1614382 (Why is no real title available?)
• scientific article; zbMATH DE number 5485439 (Why is no real title available?)
• A Note on Distributed Quantile Regression by Pilot Sampling and One-Step Updating
• A statistical framework for differential privacy
• Asymptotic Statistics
• Corrected-loss estimation for quantile regression with covariate measurement errors
• Deconvolving kernel density estimators
• Density Deconvolution With Additive Measurement Errors Using Quadratic Programming
• Differentially private empirical risk minimization
• Differentially private inference via noisy optimization
• Edge differentially private estimation in the -model via jittering and method of moments
• Efficiency in local differential privacy
• Gaussian Differential Privacy
• Measurement errors in quantile regression models
• Minimax Optimal Procedures for Locally Private Estimation
• Minimax rate for multivariate data under componentwise local differential privacy constraints
• On the optimal rates of convergence for nonparametric deconvolution problems
• Optimal Rates of Convergence for Deconvolving a Density
• Our Data, Ourselves: Privacy Via Distributed Noise Generation
• Privacy-preserving parametric inference: a case for robust statistics
• Private empirical risk minimization: efficient algorithms and tight error bounds
• Private learning and sanitization: pure vs. approximate differential privacy
• Pufferfish: a framework for mathematical privacy definitions
• Randomized response: a survey technique for eliminating evasive answer bias
• Smoothness-Penalized Deconvolution (SPeD) of a Density Estimate
• The algorithmic foundations of differential privacy
• The cost of privacy: optimal rates of convergence for parameter estimation with differential privacy
• The right complexity measure in locally private estimation: it is not the Fisher information
• Theory of Cryptography
• Unbiased estimation of a nonlinear function a normal mean with application to measurement err oorf models
• What can we learn privately?

This page was built for publication: Versatile differentially private learning for general loss functions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7227000)