The Sample Complexity of Distribution-Free Parity Learning in the Robust Shuffle Model

We provide a lowerbound on the sample complexity of distribution-free parity learning in the realizable case in the shuffle model of differential privacy. Namely, we show that the sample complexity of learning d-bit parity functions is Ω(2d/2). Our result extends a recent similar lowerbound on the s...

Full description

Saved in:
Bibliographic Details
Published inThe journal of privacy and confidentiality Vol. 12; no. 2
Main Authors Nissim, Kobbi, Yan, Chao
Format Journal Article
LanguageEnglish
Published Labor Dynamics Institute 01.11.2022
Subjects
Differential Privacy
parity learning
private learning
Online AccessGet full text

Cover

More Information
Summary:We provide a lowerbound on the sample complexity of distribution-free parity learning in the realizable case in the shuffle model of differential privacy. Namely, we show that the sample complexity of learning d-bit parity functions is Ω(2d/2). Our result extends a recent similar lowerbound on the sample complexity of private agnostic learning of parity functions in the shuffle model by Cheu and Ullman . We also sketch a simple shuffle model protocol demon- strating that our results are tight up to poly(d) factors.
ISSN:2575-8527
2575-8527
DOI:10.29012/jpc.805