One Step to Efficient Synthetic Data

TL;DR

This paper introduces a novel, computationally efficient method for generating synthetic data that ensures asymptotic efficiency, consistency with the true distribution, and strong privacy guarantees, improving over traditional sampling approaches.

Contribution

The authors propose a general, widely applicable synthetic data generation method that achieves asymptotic efficiency, consistency, and differential privacy, with theoretical and empirical validation.

Findings

The new method produces asymptotically efficient and consistent synthetic data.

It can generate both partially and fully private synthetic datasets.

The approach is computationally efficient and adaptable to various parametric models.

Abstract

A common approach to synthetic data is to sample from a fitted model. We show that under general assumptions, this approach results in a sample with inefficient estimators and whose joint distribution is inconsistent with the true distribution. Motivated by this, we propose a general method of producing synthetic data, which is widely applicable for parametric models, has asymptotically efficient summary statistics, and is both easily implemented and highly computationally efficient. Our approach allows for the construction of both partially synthetic datasets, which preserve certain summary statistics, as well as fully synthetic data which satisfy the strong guarantee of differential privacy (DP), both with the same asymptotic guarantees. We also provide theoretical and empirical evidence that the distribution from our procedure converges to the true distribution. Besides our focus on synthetic data, our procedure can also be used to perform approximate hypothesis tests in the presence of intractable likelihood functions.