Timezone: »

Contributed talk 2: Subsampled Renyi Differential Privacy and Analytical Moments Accountant
Yu-Xiang Wang

Sat Dec 08 08:15 AM -- 08:30 AM (PST) @

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) parameters for algorithms that: (1) subsample the dataset, and then (2) applies a randomized mechanism M to the subsample, in terms of the RDP parameters of M and the subsampling probability parameter. Our results generalize the moments accounting technique, developed by Abadi et al. [CCS'16] for the Gaussian mechanism, to any subsampled RDP mechanism.

Author Information

Yu-Xiang Wang (UC Santa Barbara)

More from the Same Authors