Paper ID: 2404.17714
Lower Bounds for Private Estimation of Gaussian Covariance Matrices under All Reasonable Parameter Regimes
Victor S. Portella, Nick Harvey
We prove lower bounds on the number of samples needed to privately estimate the covariance matrix of a Gaussian distribution. Our bounds match existing upper bounds in the widest known setting of parameters. Our analysis relies on the Stein-Haff identity, an extension of the classical Stein's identity used in previous fingerprinting lemma arguments.
Submitted: Apr 26, 2024