UNIGE document Chapitre d'actes
previous document  unige:73193  next document
add to browser collection
Title

Information geometry and minimum description length networks

Authors
Published in Proceedings of the 32 nd International Conference on Machine Learning. Lille, France. 2015, p. 49-58
Collection JMLR: Workshop and Conference Proceedings; 37
Abstract 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.
Keywords Information geometryMinimum description lengthMixture model
Full text
Proceedings (Published version) (1.1 MB) - public document Free access
Appendix (183 Kb) - public document Free access
Structures
Research groups Viper group
Computer Vision and Multimedia Laboratory
Citation
(ISO format)
SUN, Ke et al. Information geometry and minimum description length networks. In: Proceedings of the 32 nd International Conference on Machine Learning. Lille, France. [s.l.] : [s.n.], 2015. p. 49-58. (JMLR: Workshop and Conference Proceedings; 37) https://archive-ouverte.unige.ch/unige:73193

319 hits

101 downloads

Update

Deposited on : 2015-06-15

Export document
Format :
Citation style :