On rate optimal private regression under local differential privacy
From MaRDI portal
Publication:6400736
arXiv2206.00114MaRDI QIDQ6400736FDOQ6400736
Authors: László Györfi, Martin H. Kroll 
Publication date: 31 May 2022
Abstract: We consider the problem of estimating a regression function from anonymized data in the framework of local differential privacy. We propose a novel partitioning estimate of the regression function, derive a rate of convergence for the excess prediction risk over H"older classes, and prove a matching lower bound. In contrast to the existing literature on the problem the so-called strong density assumption on the design distribution is obsolete.
This page was built for publication: On rate optimal private regression under local differential privacy
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6400736)
