Differentially Private Low-dimensional Synthetic Data from High-dimensional Datasets
This work addresses the challenge of privacy-preserving data analysis for high-dimensional datasets, offering a solution that mitigates dimensionality issues, though it appears incremental as it builds on existing private PCA methods.
The paper tackles the problem of generating accurate differentially private synthetic data from high-dimensional datasets, which suffers from the curse of dimensionality, by proposing an algorithm that produces low-dimensional synthetic data with a utility guarantee in Wasserstein distance, achieving near-optimal accuracy bounds for private PCA without requiring a spectral gap assumption.
Differentially private synthetic data provide a powerful mechanism to enable data analysis while protecting sensitive information about individuals. However, when the data lie in a high-dimensional space, the accuracy of the synthetic data suffers from the curse of dimensionality. In this paper, we propose a differentially private algorithm to generate low-dimensional synthetic data efficiently from a high-dimensional dataset with a utility guarantee with respect to the Wasserstein distance. A key step of our algorithm is a private principal component analysis (PCA) procedure with a near-optimal accuracy bound that circumvents the curse of dimensionality. Unlike the standard perturbation analysis, our analysis of private PCA works without assuming the spectral gap for the covariance matrix.