Robustly Learning any Clusterable Mixture of Gaussians

Hopkins Samuel B.
Hopkins Samuel B.
Karmalkar Sushrut
Karmalkar Sushrut
Cited by: 0|Bibtex|Views29|Links

Abstract:

We study the efficient learnability of high-dimensional Gaussian mixtures in the outlier-robust setting, where a small constant fraction of the data is adversarially corrupted. We resolve the polynomial learnability of this problem when the components are pairwise separated in total variation distance. Specifically, we provide an algori...More

Code:

Data:

Your rating :
0

 

Tags
Comments