Private PAC learning implies finite Littlestone dimension

Abstract
We show that every approximately differentially private learning algorithm (possibly improper) for a class with Littlestone dimension~ requires examples. As a corollary it follows that the class of thresholds over 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 arXivComments on this paper