English

Multiclass versus Binary Differentially Private PAC Learning

Machine Learning 2021-07-26 v1 Data Structures and Algorithms

Abstract

We show a generic reduction from multiclass differentially private PAC learning to binary private PAC learning. We apply this transformation to a recently proposed binary private PAC learner to obtain a private multiclass learner with sample complexity that has a polynomial dependence on the multiclass Littlestone dimension and a poly-logarithmic dependence on the number of classes. This yields an exponential improvement in the dependence on both parameters over learners from previous work. Our proof extends the notion of Ψ\Psi-dimension defined in work of Ben-David et al. [JCSS '95] to the online setting and explores its general properties.

Cite

@article{arxiv.2107.10870,
  title  = {Multiclass versus Binary Differentially Private PAC Learning},
  author = {Mark Bun and Marco Gaboardi and Satchit Sivakumar},
  journal= {arXiv preprint arXiv:2107.10870},
  year   = {2021}
}
R2 v1 2026-06-24T04:26:34.142Z