Private Algorithms Can Always Be Extended

arXiv: Statistics Theory, Volume abs/1810.12518, 2018.

Cited by: 3|Bibtex|Views54
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com|arxiv.org

Abstract:

We consider the following fundamental question on $epsilon$-differential privacy. Consider an arbitrary $epsilon$-differentially private algorithm defined on a subset of the input space. Is it possible to extend it to an $epsilonu0027$-differentially private algorithm on the whole input space for some $epsilonu0027$ comparable with $epsil...More

Code:

Data:

Your rating :
0

 

Tags
Comments