Open Problem: Improper Learning of Mixtures of Gaussians

Elad Hazan; Roi Livni

Open Problem: Improper Learning of Mixtures of Gaussians

Research output: Contribution to journal › Conference article › peer-review

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.

Original language	English (US)
Pages (from-to)	3399-3402
Number of pages	4
Journal	Proceedings of Machine Learning Research
Volume	75
State	Published - 2018
Event	31st Annual Conference on Learning Theory, COLT 2018 - Stockholm, Sweden Duration: Jul 6 2018 → Jul 9 2018

All Science Journal Classification (ASJC) codes

Software
Control and Systems Engineering
Statistics and Probability
Artificial Intelligence

Cite this

@article{f021b9556ca941f4a3ebaeec998afc3d,

title = "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.",

author = "Elad Hazan and Roi Livni",

note = "Publisher Copyright: {\textcopyright} 2018 E. Hazan \& R. Livni.; 31st Annual Conference on Learning Theory, COLT 2018 ; Conference date: 06-07-2018 Through 09-07-2018",

year = "2018",

language = "English (US)",

volume = "75",

pages = "3399--3402",

journal = "Proceedings of Machine Learning Research",

issn = "2640-3498",

publisher = "ML Research Press",

}

TY - JOUR

T1 - Open Problem

T2 - 31st Annual Conference on Learning Theory, COLT 2018

AU - Hazan, Elad

AU - Livni, Roi

PY - 2018

Y1 - 2018

N2 - 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.

AB - 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.

UR - https://www.scopus.com/pages/publications/85162158980

UR - https://www.scopus.com/inward/citedby.url?scp=85162158980&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:85162158980

SN - 2640-3498

VL - 75

SP - 3399

EP - 3402

JO - Proceedings of Machine Learning Research

JF - Proceedings of Machine Learning Research

Y2 - 6 July 2018 through 9 July 2018

ER -

Open Problem: Improper Learning of Mixtures of Gaussians

Abstract

All Science Journal Classification (ASJC) codes

Other files and links

Fingerprint

Cite this