Counting on Dummies: Privacy Amplification with Observable Counts and Truncated Batches

The paper introduces a simple mechanism that adds a random number of dummy points to protect batch size information in Differentially Private Stochastic Gradient Descent (DP‑SGD). This approach addresses privacy amplification challenges arising from variable batch sizes and truncation in both centralized and distributed settings. The authors provide a general analysis for Poisson sampling and random allocation, showing that the expected number of dummy points is asymptotically smaller than directly privatizing batch sizes, and demonstrate empirically that their method outperforms recent truncation accounting techniques.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

• safety