Open problem: Improper learning of mixtures of Gaussians

[edit]

Elad Hazan, Livni Roi ;
Proceedings of the 31st Conference On Learning Theory, PMLR 75:3399-3402, 2018.

Abstract

We ask whether there exists an efficient unsupervised learning algorithm for mixture of Gaussians in the over-complete case (number of mixtures is larger than the dimension). The notion of learning is taken to be worst-case compression-based, to allow for improper learning.

Related Material