On the Sample Complexity of Privately Learning Unbounded High-Dimensional Gaussians
This addresses the challenge of privately learning high-dimensional Gaussians, which is incremental as it builds on recent techniques for differentially private hypothesis selection.
The paper tackles the problem of agnostically learning multivariate Gaussians under approximate differential privacy, providing the first finite sample upper bounds without parameter restrictions, with near-optimal bounds for identity covariance and conjectured near-optimality in general cases.
We provide sample complexity upper bounds for agnostically learning multivariate Gaussians under the constraint of approximate differential privacy. These are the first finite sample upper bounds for general Gaussians which do not impose restrictions on the parameters of the distribution. Our bounds are near-optimal in the case when the covariance is known to be the identity, and conjectured to be near-optimal in the general case. From a technical standpoint, we provide analytic tools for arguing the existence of global "locally small" covers from local covers of the space. These are exploited using modifications of recent techniques for differentially private hypothesis selection. Our techniques may prove useful for privately learning other distribution classes which do not possess a finite cover.