15
1

Generalizing DP-SGD with Shuffling and Batch Clipping

Abstract

Classical differential private DP-SGD implements individual clipping with random subsampling, which forces a mini-batch SGD approach. We provide a general differential private algorithmic framework that goes beyond DP-SGD and allows any possible first order optimizers (e.g., classical SGD and momentum based SGD approaches) in combination with batch clipping, which clips an aggregate of computed gradients rather than summing clipped gradients (as is done in individual clipping). The framework also admits sampling techniques beyond random subsampling such as shuffling. Our DP analysis follows the ff-DP approach and introduces a new proof technique which allows us to derive simple closed form expressions and to also analyse group privacy. In particular, for EE epochs work and groups of size gg, we show a gE\sqrt{g E} DP dependency for batch clipping with shuffling.

View on arXiv
Comments on this paper