Information geometry and minimum description length networks

Sun, Ke ( Computer Vision and Multimedia Laboratory, University of Geneva, Switzerland) ; Wang, Jun ( Expedia, Switzerland) ; Kalousis, Alexandros ( Haute école de gestion de Genève, HES-SO // Haute Ecole Spécialisée de Suisse Occidentale) ; Marchand-Maillet, Stéphane ( Computer Vision and Multimedia Laboratory, University of Geneva, Switzerland )

We study parametric unsupervised mixture learning. We measure the loss of intrinsic information from the observations to complex mixture models, and then to simple mixture models. We present a geometric picture, where all these representations are regarded as free points in the space of probability distributions. Based on minimum description length, we derive a simple geometric principle to learn all these models together. We present a new learning machine with theories, algorithms, and simulations.


Conference Type:
full paper
Faculty:
Economie et Services
School:
HEG - Genève
Institute:
CRAG - Centre de Recherche Appliquée en Gestion
Subject(s):
Informatique
Publisher:
[S.l.] , Journal of machine learning research
Date:
[S.l.]
Journal of machine learning research
2015
Pagination:
10 p.
Published in:
Journal of machine learning research : proceedings of the 32nd International Conference on Machine Learning, pp. 49–58, 2015
Numeration (vol. no.):
2015, vol. 37, pp. 49–58
ISSN:
1938-7228
External resources:
Appears in Collection:



 Record created 2015-11-12, last modified 2019-06-11

Fulltext:
Download fulltext
PDF

Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)