Private PAC learning implies finite Littlestone dimension

📝 Original Info

• Title: Private PAC learning implies finite Littlestone dimension
• ArXiv ID: 1806.00949
• Date: 2019-03-11
• Authors: Noga Alon and Roi Livni and Maryanthe Malliaris and Shay Moran

📝 Abstract

We show that every approximately differentially private learning algorithm (possibly improper) for a class $H$ with Littlestone dimension~$d$ requires $\Omega\bigl(\log^*(d)\bigr)$ examples. As a corollary it follows that the class of thresholds over $\mathbb{N}$ 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.

📄 Full Content

Reference