Work

Information decomposition on structured space

Year: 2016

Type: conference-paper

Abstract: 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.

Source: IEEE International Symposium on Information Theory (ISIT)

DOI: 10.1109/isit.2016.7541364

Authors: Mahito Sugiyama, Hiroyuki Nakahara, Koji Tsuda

Institutions: Japan Science and Technology Agency, The University of Osaka, RIKEN Center for Brain Science, RIKEN, The University of Tokyo

Language: English

Topic: Bayesian Modeling and Causal Inference

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: Japan Society for the Promotion of Science

Award: Foundations of knowledge synthesis based on selection of concept and creation of pivots for high-dimensional feature space