Differentially-Private Bayes Consistency

TL;DR

This paper introduces a universally Bayes consistent learning rule that satisfies differential privacy, enabling private learning of arbitrary distributions and surpassing limitations of the distribution-free PAC model.

Contribution

It presents the first universally consistent differentially private learner for binary classification and density estimation, demonstrating new possibilities in private learning.

Findings

Universal DP learner for binary classification and density estimation.

Private learning of arbitrary distributions with a single DP algorithm.

Near-optimal labeled sample complexity for VC classes in semi-supervised learning.

Abstract

We construct a universally Bayes consistent learning rule that satisfies differential privacy (DP). We first handle the setting of binary classification and then extend our rule to the more general setting of density estimation (with respect to the total variation metric). The existence of a universally consistent DP learner reveals a stark difference with the distribution-free PAC model. Indeed, in the latter DP learning is extremely limited: even one-dimensional linear classifiers are not privately learnable in this stringent model. Our result thus demonstrates that by allowing the learning rate to depend on the target distribution, one can circumvent the above-mentioned impossibility result and in fact, learn \emph{arbitrary} distributions by a single DP algorithm. As an application, we prove that any VC class can be privately learned in a semi-supervised setting with a near-optimal \emph{labeled} sample complexity of $\tilde{O}(d/\varepsilon)$ labeled examples (and with an unlabeled sample complexity that can depend on the target distribution).