Tight Group-Level DP Guarantees for DP-SGD with Sampling via Mixture of Gaussians Mechanisms

Abstract

We give a procedure for computing group-level $(\epsilon ,\delta )$-DP guarantees for DP-SGD, when using Poisson sampling or fixed batch size sampling. Up to discretization errors in the implementation, the DP guarantees computed by this procedure are tight (assuming we release every intermediate iterate).

v2: Added links to open-source implementation of PLD accounting for MoG mechanisms