Density estimation under local differential privacy and Hellinger loss

DOI10.3150/22-BEJ1543OpenAlexW4200632342MaRDI QIDQ6160979FDOQ6160979

Authors Mathieu Sart 

Publication date 2 June 2023

Published in Bernoulli (Search for Journal in Brave)

Full work available at URL https://projecteuclid.org/journals/bernoulli/volume-29/issue-3/Density-estimation-under-local-differential-privacy-and-Hellinger-loss/10.3150/22-BEJ1543.full

zbMATH Keywords

density estimationBesov spacesminimax estimationlocal differential privacy

Mathematics Subject Classification ID

Nonparametric inference (62Gxx) Stochastic processes (60Gxx) Inference from stochastic processes (62Mxx)

Cites Work

• A statistical framework for differential privacy
• Advanced Lectures on Machine Learning
• Asymptotically Minimax Adaptive Estimation. I: Upper Bounds. Optimally Adaptive Estimates
• Combinatorial methods in density estimation
• Concentration inequalities and model selection. Ecole d'Eté de Probabilités de Saint-Flour XXXIII -- 2003.
• Concentration inequalities. A nonasymptotic theory of independence
• Degree of Adaptive Approximation
• Differential privacy for functions and functional data
• Estimating a density, a hazard rate, and a transition intensity via the \(\rho\)-estimation method
• Estimating the intensity of a random measure by histogram type estimators
• Estimation of the transition density of a Markov chain
• Estimator selection with respect to Hellinger-type risks
• Geometrizing rates of convergence under local differential privacy constraints
• Inhomogeneous and anisotropic conditional density estimation from dependent data
• Learning Theory
• Local differential privacy: elbow effect in optimal density estimation and adaptation over Besov ellipsoids
• Minimax Optimal Procedures for Locally Private Estimation
• Minimax bounds for Besov classes in density estimation
• Minimax optimal goodness-of-fit testing for densities and multinomials under a local differential privacy constraint
• Model selection for density estimation with \(\mathbb L_2\)-loss
• Model selection via testing: an alternative to (penalized) maximum likelihood estimators.
• On density estimation at a fixed point under local differential privacy
• Risk bounds for model selection via penalization
• Strongly universally consistent nonparametric regression and classification with privatised data

Cited In (3)

• Separating Local & Shuffled Differential Privacy via Histograms
• Multivariate density estimation from privatised data: universal consistency and minimax rates
• Title not available (Why is no real title available?)

This page was built for publication: Density estimation under local differential privacy and Hellinger loss

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6160979)