English

Statistical Theory of Differentially Private Marginal-based Data Synthesis Algorithms

Machine Learning 2023-01-26 v2 Machine Learning

Abstract

Marginal-based methods achieve promising performance in the synthetic data competition hosted by the National Institute of Standards and Technology (NIST). To deal with high-dimensional data, the distribution of synthetic data is represented by a probabilistic graphical model (e.g., a Bayesian network), while the raw data distribution is approximated by a collection of low-dimensional marginals. Differential privacy (DP) is guaranteed by introducing random noise to each low-dimensional marginal distribution. Despite its promising performance in practice, the statistical properties of marginal-based methods are rarely studied in the literature. In this paper, we study DP data synthesis algorithms based on Bayesian networks (BN) from a statistical perspective. We establish a rigorous accuracy guarantee for BN-based algorithms, where the errors are measured by the total variation (TV) distance or the L2L^2 distance. Related to downstream machine learning tasks, an upper bound for the utility error of the DP synthetic data is also derived. To complete the picture, we establish a lower bound for TV accuracy that holds for every ϵ\epsilon-DP synthetic data generator.

Keywords

Cite

@article{arxiv.2301.08844,
  title  = {Statistical Theory of Differentially Private Marginal-based Data Synthesis Algorithms},
  author = {Ximing Li and Chendi Wang and Guang Cheng},
  journal= {arXiv preprint arXiv:2301.08844},
  year   = {2023}
}
R2 v1 2026-06-28T08:16:45.500Z