Simultaneous private learning of multiple concepts

Mark Bun, Kobbi Nissim, Uri Stemmer

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

12 Scopus citations

Abstract

We investigate the direct-sum problem in the context of differentially private PAC learning: What is the sample complexity of solving k learning tasks simultaneously under differential privacy, and how does this cost compare to that of solving k learning tasks without privacy? In our setting, an individual example consists of a domain element x labeled by k unknown concepts (c1; ck). The goal of a multi-learner is to output k hypotheses (h1; hk) that generalize the input examples. Without concern for privacy, the sample complexity needed to simultaneously learn k concepts is essentially the same as needed for learning a single concept. Under differential privacy, the basic strategy of learning each hypothesis independently yields sample complexity that grows polynomially with k. For some concept classes, we give multi-learners that require fewer samples than the basic strategy. Unfortunately, however, we also give lower bounds showing that even for very simple concept classes, the sample cost of private multi-learning must grow polynomially in k.

Original languageEnglish
Title of host publicationITCS 2016 - Proceedings of the 2016 ACM Conference on Innovations in Theoretical Computer Science
PublisherAssociation for Computing Machinery, Inc
Pages369-380
Number of pages12
ISBN (Electronic)9781450340571
DOIs
StatePublished - 14 Jan 2016
Event7th ACM Conference on Innovations in Theoretical Computer Science, ITCS 2016 - Cambridge, United States
Duration: 14 Jan 201616 Jan 2016

Publication series

NameITCS 2016 - Proceedings of the 2016 ACM Conference on Innovations in Theoretical Computer Science

Conference

Conference7th ACM Conference on Innovations in Theoretical Computer Science, ITCS 2016
Country/TerritoryUnited States
CityCambridge
Period14/01/1616/01/16

Keywords

  • Agnostic learning
  • Differential privacy
  • Directsum
  • PAC learning

Fingerprint

Dive into the research topics of 'Simultaneous private learning of multiple concepts'. Together they form a unique fingerprint.

Cite this