A Better Bound Gives a Hundred Rounds: Enhanced Privacy Guarantees via f-Divergences

Shahab Asoodeh, Jiachun Liao, Flavio P. Calmon, Oliver Kosut, Lalitha Sankar

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We derive the optimal differential privacy (DP) parameters of a mechanism that satisfies a given level of Renyí differential privacy (RDP). Our result is based on the joint range of two f-divergences that underlie the approximate and the Renyi variations of differential privacy. We apply our result tó the moments accountant framework for characterizing privacy guarantees of stochastic gradient descent. When compared to the state-of-the-art, our bounds may lead to about 100 more stochastic gradient descent iterations for training deep learning models for the same privacy budget.

Original languageEnglish (US)
Title of host publication2020 IEEE International Symposium on Information Theory, ISIT 2020 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages920-925
Number of pages6
ISBN (Electronic)9781728164328
DOIs
StatePublished - Jun 2020
Event2020 IEEE International Symposium on Information Theory, ISIT 2020 - Los Angeles, United States
Duration: Jul 21 2020Jul 26 2020

Publication series

NameIEEE International Symposium on Information Theory - Proceedings
Volume2020-June
ISSN (Print)2157-8095

Conference

Conference2020 IEEE International Symposium on Information Theory, ISIT 2020
CountryUnited States
CityLos Angeles
Period7/21/207/26/20

ASJC Scopus subject areas

  • Theoretical Computer Science
  • Information Systems
  • Modeling and Simulation
  • Applied Mathematics

Fingerprint Dive into the research topics of 'A Better Bound Gives a Hundred Rounds: Enhanced Privacy Guarantees via f-Divergences'. Together they form a unique fingerprint.

  • Cite this

    Asoodeh, S., Liao, J., Calmon, F. P., Kosut, O., & Sankar, L. (2020). A Better Bound Gives a Hundred Rounds: Enhanced Privacy Guarantees via f-Divergences. In 2020 IEEE International Symposium on Information Theory, ISIT 2020 - Proceedings (pp. 920-925). [9174015] (IEEE International Symposium on Information Theory - Proceedings; Vol. 2020-June). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISIT44484.2020.9174015