Optimal Estimation in High-Dimensional Gaussian Mixtures

• Activity Number: 586 - Theoretical Investigations on Discrete Structure Recovery
• Type: Topic Contributed
• Date/Time: Thursday, August 6, 2020 : 3:00 PM to 4:50 PM
• Sponsor: IMS
• Author(s): Natalie Doss*
• Companies: Yale University
• Keywords: Minimax rates; Non-convex optimization; Statistical theory; Mixtures; Density estimation; Parameter estimation

Abstract

The Gaussian location mixture model is one of the most widely studied models in the statistical literature, yet rates of convergence in this model are not well understood when the model is high dimensional. I will discuss recent results on minimax rates of convergence for both parameter and density estimation. I will also discuss a fast algorithm for mixing distribution estimation that achieves the minimax rate.