Proceedings chapter
Open access

Information geometry and minimum description length networks

Presented at Lille, France
  • JMLR: Workshop and Conference Proceedings; 37
Publication date2015

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.

  • Information geometry
  • Minimum description length
  • Mixture model
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)
Main files (1)
Proceedings chapter (Published version)
Secondary files (1)
  • PID : unige:73193

Technical informations

Creation06/11/2015 12:35:00 PM
First validation06/11/2015 12:35:00 PM
Update time03/14/2023 11:22:37 PM
Status update03/14/2023 11:22:36 PM
Last indexation10/18/2023 11:07:53 PM
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack