Classification under local differential privacy
Statistics Theory
2019-12-11 v1 Methodology
Machine Learning
Statistics Theory
Abstract
We consider the binary classification problem in a setup that preserves the privacy of the original sample. We provide a privacy mechanism that is locally differentially private and then construct a classifier based on the private sample that is universally consistent in Euclidean spaces. Under stronger assumptions, we establish the minimax rates of convergence of the excess risk and see that they are slower than in the case when the original sample is available.
Cite
@article{arxiv.1912.04629,
title = {Classification under local differential privacy},
author = {Thomas Berrett and Cristina Butucea},
journal= {arXiv preprint arXiv:1912.04629},
year = {2019}
}
Comments
12 pages