Subsampled Rényi Differential Privacy and Analytical Moments Accountant

We study the problem of subsampling in differential privacy (DP), a question that is the centerpiece behind many successful differentially private machine learning algorithms. Specifically, we provide a tight upper bound on the Renyi Differential Privacy (RDP) [Mironov, 2017] parameters for algorit...

Full description

Bibliographic Details
Main Authors: Yu-Xiang Wang, Borja Balle, Shiva Kasiviswanathan
Format: Article
Language:English
Published: Labor Dynamics Institute 2020-06-01
Series:The Journal of Privacy and Confidentiality
Subjects:
Online Access:https://journalprivacyconfidentiality.org/index.php/jpc/article/view/723