13
109

Private PAC learning implies finite Littlestone dimension

Abstract

We show that every approximately differentially private learning algorithm (possibly improper) for a class HH with Littlestone dimension~dd requires Ω(log(d))\Omega\bigl(\log^*(d)\bigr) examples. As a corollary it follows that the class of thresholds over N\mathbb{N} can not be learned in a private manner; this resolves open question due to [Bun et al., 2015, Feldman and Xiao, 2015]. We leave as an open question whether every class with a finite Littlestone dimension can be learned by an approximately differentially private algorithm.

View on arXiv
Comments on this paper