Technical Program

Paper Detail

Paper IDP.4.4
Paper Title A Better Bound Gives a Hundred Rounds: Enhanced Privacy Guarantees via f-Divergences
Authors Shahab Asoodeh, Harvard University, United States; Jiachun Liao, Arizona State University, United States; Flavio P. Calmon, Harvard University, United States; Oliver Kosut, Lalitha Sankar, Arizona State University, United States
Session P.4: Information Privacy II
Presentation Lecture
Track Cryptography, Security and Privacy
Manuscript  Click here to download the manuscript
Virtual Presentation  Click here to watch in the Virtual Symposium
Abstract We derive the optimal differential privacy (DP) parameters of a mechanism that satisfies a given level of Renyi 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 to 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.

Plan Ahead


2021 IEEE International Symposium on Information Theory

11-16 July 2021 | Melbourne, Victoria, Australia

Visit Website!