New Oracle-Efficient Algorithms for Private Synthetic Data Release

TL;DR

This paper introduces three oracle-efficient algorithms for differentially private synthetic data generation, offering improved accuracy and scalability over existing methods, with strong theoretical guarantees and empirical validation.

Contribution

The paper proposes novel oracle-efficient algorithms for private synthetic data release that are computationally practical and outperform current methods in accuracy under high privacy constraints.

Findings

Algorithms achieve differential privacy with theoretical guarantees.

Empirical results show better accuracy in high privacy regimes.

Methods scale well with data dimensionality and query complexity.

Abstract

We present three new algorithms for constructing differentially private synthetic data---a sanitized version of a sensitive dataset that approximately preserves the answers to a large collection of statistical queries. All three algorithms are \emph{oracle-efficient} in the sense that they are computationally efficient when given access to an optimization oracle. Such an oracle can be implemented using many existing (non-private) optimization tools such as sophisticated integer program solvers. While the accuracy of the synthetic data is contingent on the oracle's optimization performance, the algorithms satisfy differential privacy even in the worst case. For all three algorithms, we provide theoretical guarantees for both accuracy and privacy. Through empirical evaluation, we demonstrate that our methods scale well with both the dimensionality of the data and the number of queries. Compared to the state-of-the-art method High-Dimensional Matrix Mechanism \cite{McKennaMHM18}, our algorithms provide better accuracy in the large workload and high privacy regime (corresponding to low privacy loss $\varepsilon$).