Private and polynomial time algorithms for learning Gaussians and beyond

• Published in: arXiv.org
• Main Authors: Ashtiani, Hassan, Liaw, Christopher
• Format: Paper
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 22.06.2022
• Subjects: Algorithms; Complexity; Information theory; Machine learning; Polynomials; Upper bounds

We present a fairly general framework for reducing \((\varepsilon, \delta)\) differentially private (DP) statistical estimation to its non-private counterpart. As the main application of this framework, we give a polynomial time and \((\varepsilon,\delta)\)-DP algorithm for learning (unrestricted) G...