Open Problem: Improper Learning of Mixtures of Gaussians

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.

Cite

Text

Hazan and Livni. "Open Problem: Improper Learning of Mixtures of Gaussians." Annual Conference on Computational Learning Theory, 2018.

Markdown

[Hazan and Livni. "Open Problem: Improper Learning of Mixtures of Gaussians." Annual Conference on Computational Learning Theory, 2018.](https://mlanthology.org/colt/2018/hazan2018colt-open/)

BibTeX

@inproceedings{hazan2018colt-open,
  title     = {{Open Problem: Improper Learning of Mixtures of Gaussians}},
  author    = {Hazan, Elad and Livni, Roi},
  booktitle = {Annual Conference on Computational Learning Theory},
  year      = {2018},
  pages     = {3399-3402},
  url       = {https://mlanthology.org/colt/2018/hazan2018colt-open/}
}