Mixtures of Gaussians are Privately Learnable with a Polynomial Number of Samples

7 September 2023

Papers citing "Mixtures of Gaussians are Privately Learnable with a Polynomial Number of Samples"

10 / 10 papers shown

Title
Sample-Optimal Locally Private Hypothesis Selection and the Provable Benefits of Interactivity A. F. Pour Hassan Ashtiani S. Asoodeh 38 0 0 09 Dec 2023
Private Distribution Learning with Public Data: The View from Sample Compression Shai Ben-David Alex Bie C. Canonne Gautam Kamath Vikrant Singhal 35 11 0 11 Aug 2023
Improving the Utility of Differentially Private Clustering through Dynamical Processing Junyoung Byun Yujin Choi Jaewoo Lee 11 1 0 27 Apr 2023
Polynomial Time and Private Learning of Unbounded Gaussian Mixture Models Jamil Arbas H. Ashtiani Christopher Liaw 40 23 0 07 Mar 2023
Privacy Induces Robustness: Information-Computation Gaps and Sparse Mean Estimation Kristian Georgiev Samuel B. Hopkins FedML 33 21 0 01 Nov 2022
New Lower Bounds for Private Estimation and a Generalized Fingerprinting Lemma Gautam Kamath Argyris Mouzakis Vikrant Singhal FedML 34 26 0 17 May 2022
A Private and Computationally-Efficient Estimator for Unbounded Gaussians Gautam Kamath Argyris Mouzakis Vikrant Singhal Thomas Steinke Jonathan R. Ullman 55 39 0 08 Nov 2021
Robust and Differentially Private Mean Estimation Xiyang Liu Weihao Kong Sham Kakade Sewoong Oh OOD FedML 53 75 0 18 Feb 2021
On the Sample Complexity of Privately Learning Unbounded High-Dimensional Gaussians Ishaq Aden-Ali H. Ashtiani Gautam Kamath 40 41 0 19 Oct 2020
Privately Learning High-Dimensional Distributions Gautam Kamath Jerry Li Vikrant Singhal Jonathan R. Ullman FedML 69 148 0 01 May 2018