Open problem: Improper learning of mixtures of Gaussians

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.

Cite this Paper


BibTeX
@InProceedings{pmlr-v75-hazan18a, title = {Open problem: Improper learning of mixtures of {G}aussians}, author = {Hazan, Elad and Roi, Livni}, booktitle = {Proceedings of the 31st Conference On Learning Theory}, pages = {3399--3402}, year = {2018}, editor = {Bubeck, S├ębastien and Perchet, Vianney and Rigollet, Philippe}, volume = {75}, series = {Proceedings of Machine Learning Research}, month = {06--09 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v75/hazan18a/hazan18a.pdf}, url = {https://proceedings.mlr.press/v75/hazan18a.html}, 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.} }
Endnote
%0 Conference Paper %T Open problem: Improper learning of mixtures of Gaussians %A Elad Hazan %A Livni Roi %B Proceedings of the 31st Conference On Learning Theory %C Proceedings of Machine Learning Research %D 2018 %E S├ębastien Bubeck %E Vianney Perchet %E Philippe Rigollet %F pmlr-v75-hazan18a %I PMLR %P 3399--3402 %U https://proceedings.mlr.press/v75/hazan18a.html %V 75 %X 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.
APA
Hazan, E. & Roi, L.. (2018). Open problem: Improper learning of mixtures of Gaussians. Proceedings of the 31st Conference On Learning Theory, in Proceedings of Machine Learning Research 75:3399-3402 Available from https://proceedings.mlr.press/v75/hazan18a.html.

Related Material