Balls-and-Bins Sampling for DP-SGD
This addresses the problem of balancing privacy and utility in DP-SGD for machine learning practitioners, offering an incremental improvement over existing sampling methods.
The paper tackles the privacy-utility trade-off in differentially private stochastic gradient descent (DP-SGD) by introducing Balls-and-Bins sampling, which achieves utility comparable to shuffling while providing privacy amplification similar to or better than Poisson subsampling in practical parameter regimes.
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.