Limits of private learning with access to public data

Noga Alon, Raef Bassily, Shay Moran

Research output: Contribution to journalConference articlepeer-review

25 Scopus citations

Abstract

We consider learning problems where the training set consists of two types of examples: private and public. The goal is to design a learning algorithm that satisfies differential privacy only with respect to the private examples. This setting interpolates between private learning (where all examples are private) and classical learning (where all examples are public). We study the limits of learning in this setting in terms of private and public sample complexities. We show that any hypothesis class of VC-dimension d can be agnostically learned up to an excess error of a using only (roughly) d/a public examples and d/a2 private labeled examples. This result holds even when the public examples are unlabeled. This gives a quadratic improvement over the standard d/a2 upper bound on the public sample complexity (where private examples can be ignored altogether if the public examples are labeled). Furthermore, we give a nearly matching lower bound, which we prove via a generic reduction from this setting to the one of private learning without public data.

Original languageEnglish (US)
JournalAdvances in Neural Information Processing Systems
Volume32
StatePublished - 2019
Event33rd Annual Conference on Neural Information Processing Systems, NeurIPS 2019 - Vancouver, Canada
Duration: Dec 8 2019Dec 14 2019

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing

Fingerprint

Dive into the research topics of 'Limits of private learning with access to public data'. Together they form a unique fingerprint.

Cite this