Information Geometry and Minimum Description Length Networks
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.
Cite
Text
Sun et al. "Information Geometry and Minimum Description Length Networks." International Conference on Machine Learning, 2015.Markdown
[Sun et al. "Information Geometry and Minimum Description Length Networks." International Conference on Machine Learning, 2015.](https://mlanthology.org/icml/2015/sun2015icml-information/)BibTeX
@inproceedings{sun2015icml-information,
title = {{Information Geometry and Minimum Description Length Networks}},
author = {Sun, Ke and Wang, Jun and Kalousis, Alexandros and Marchand-Maillet, Stephan},
booktitle = {International Conference on Machine Learning},
year = {2015},
pages = {49-58},
volume = {37},
url = {https://mlanthology.org/icml/2015/sun2015icml-information/}
}