Gaussian Approximation for Composition and Subsampling of Differentially Private Algorithms
Read the original on arXiv Machine Learning →The paper presents a Gaussian approximation for the privacy loss distribution in differentially private stochastic gradient descent (DP‑SGD) when subsampling is used. It shows that, after truncating rare large losses, the privacy loss behaves like a Gaussian with the same mean and variance, up to a small shift that grows only logarithmically with the error tolerance. This leads to tighter variance‑based bounds for subsampled mechanisms, improving upon previous Renyi‑divergence analyses and explaining the effectiveness of the connect‑the‑dots method for random allocation sampling.
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.