Information decomposition on structured space

Mahito Sugiyama, Hiroyuki Nakahara, Koji Tsuda
2016 2016 IEEE International Symposium on Information Theory (ISIT)  
We build information geometry for a partially ordered set of variables and define the orthogonal decomposition of information theoretic quantities. The natural connection between information geometry and order theory leads to efficient decomposition algorithms. This generalization of Amari's seminal work on hierarchical decomposition of probability distributions on event combinations enables us to analyze high-order statistical interactions arising in neuroscience, biology, and machine learning.
doi:10.1109/isit.2016.7541364 dblp:conf/isit/SugiyamaNT16 fatcat:krxgxlqnnba2vlzxbwczyyvp74