We introduce the Balls-and-Bins sampling for differentially private (DP) optimization methods such as DP-SGD. While it has been common practice to use some form of shuffling in DP-SGD implementations, privacy accounting algorithms have typically assumed that Poisson subsampling is used instead. Recent work by Chua et al. (ICML 2024), however, pointed out that shuffling based DP-SGD can have a much larger privacy cost in practical regimes of parameters. In this work we show that the Balls-and-Bins sampling achieves the "best-of-both" samplers, namely, the implementation of Balls-and-Bins sampling is similar to that of Shuffling and models trained using DP-SGD with Balls-and-Bins sampling achieve utility comparable to those trained using DP-SGD with Shuffling at the same noise multiplier, and yet, Balls-and-Bins sampling enjoys similar-or-better privacy amplification as compared to Poisson subsampling in practical regimes.
@article{arxiv.2412.16802,
title = {Balls-and-Bins Sampling for DP-SGD},
author = {Lynn Chua and Badih Ghazi and Charlie Harrison and Ethan Leeman and Pritish Kamath and Ravi Kumar and Pasin Manurangsi and Amer Sinha and Chiyuan Zhang},
journal= {arXiv preprint arXiv:2412.16802},
year = {2025}
}