Paperlane

no. 2 · Monday 26 October 2026

Differentially Private Synthetic Data via Generalized Moment Matching

Rundong Ding, Yiyun He and Yizhe Zhu

math.IT · v2 · 53 pp

Abstract

We study $(\varepsilon,δ)$-differentially private synthetic data for arbitrary databases of $n$ records in $[-1,1]^d$ under a specified integral probability metric (IPM). We introduce generalized moment matching, which estimates moments privately, fits a probability measure, and samples synthetic records. A general error theorem applies when moment error controls the target IPM. This framework extends Chebyshev moment matching for $1$-Wasserstein distance and smooth queries. We apply the framework to maximum mean discrepancy with Matern and Laplace kernels and a two-layer ReLU neural tangent kernel. We also obtain guarantees for sliced Wasserstein-$1$ and the IPM induced by norm-bounded ReLU networks. With sufficiently many synthetic records,these rates are minimax optimal up to logarithmic factors for fixed dimension.

comments
53 pages
fields
Information Theory, Probability, Statistics Theory
pdf ↗ page arXiv:2610.30196 ↗