11
2

Online Differentially Private Synthetic Data Generation

Yiyun He
Roman Vershynin
Yizhe Zhu
Abstract

We present a polynomial-time algorithm for online differentially private synthetic data generation. For a data stream within the hypercube [0,1]d[0,1]^d and an infinite time horizon, we develop an online algorithm that generates a differentially private synthetic dataset at each time tt. This algorithm achieves a near-optimal accuracy bound of O(t1/dlog(t))O(t^{-1/d}\log(t)) for d2d\geq 2 and O(t1log4.5(t))O(t^{-1}\log^{4.5}(t)) for d=1d=1 in the 1-Wasserstein distance. This result generalizes the previous work on the continual release model for counting queries to include Lipschitz queries. Compared to the offline case, where the entire dataset is available at once, our approach requires only an extra polylog factor in the accuracy bound.

View on arXiv
Comments on this paper