Robustly Learning Mixtures of $k$ Arbitrary Gaussians

Ainesh Bakshi
Ainesh Bakshi
He Jia
He Jia
Pravesh K. Kothari
Pravesh K. Kothari
Santosh S. Vempala
Santosh S. Vempala
Cited by: 0|Bibtex|Views6
Other Links: arxiv.org

Abstract:

We give a polynomial-time algorithm for the problem of robustly estimating a mixture of $k$ arbitrary Gaussians in $\mathbb{R}^d$, for any fixed $k$, in the presence of a constant fraction of arbitrary corruptions. This resolves the main open problem in several previous works on algorithmic robust statistics, which addressed the special...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments