English

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

Machine Learning 2021-03-30 v1 Cryptography and Security

Abstract

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 dd-bit parity functions is Ω(2d/2)\Omega(2^{d/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 demonstrating that our results are tight up to poly(d)poly(d) factors.

Keywords

Cite

@article{arxiv.2103.15690,
  title  = {The Sample Complexity of Distribution-Free Parity Learning in the Robust Shuffle Model},
  author = {Kobbi Nissim and Chao Yan},
  journal= {arXiv preprint arXiv:2103.15690},
  year   = {2021}
}
R2 v1 2026-06-24T00:39:17.848Z