Entropy 2012, 14(3), 456-479; doi:10.3390/e14030456
Article

The Mathematical Structure of Information Bottleneck Methods

1,* email, 2email and 3email
Received: 2 December 2011; in revised form: 7 February 2012 / Accepted: 24 February 2012 / Published: 1 March 2012
(This article belongs to the Special Issue The Information Bottleneck Method)
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Abstract: Information Bottleneck-based methods use mutual information as a distortion function in order to extract relevant details about the structure of a complex system by compression. One of the approaches used to generate optimal compressed representations is by annealing a parameter. In this manuscript we present a common framework for the study of annealing in information distortion problems. We identify features that should be common to any annealing optimization problem. The main mathematical tools that we use come from the analysis of dynamical systems in the presence of symmetry (equivariant bifurcation theory). Through the compression problem, we make connections to the world of combinatorial optimization and pattern recognition. The two approaches use very different vocabularies and consider different problems to be “interesting”. We provide an initial link, through the Normalized Cut Problem, where the two disciplines can exchange tools and ideas.
Keywords: information distortion; spontaneous symmetry breaking; bifurcations; phase transition
PDF Full-text Download PDF Full-Text [221 KB, uploaded 1 March 2012 15:19 CET]

Export to BibTeX |
EndNote


MDPI and ACS Style

Gedeon, T.; Parker, A.E.; Dimitrov, A.G. The Mathematical Structure of Information Bottleneck Methods. Entropy 2012, 14, 456-479.

AMA Style

Gedeon T, Parker AE, Dimitrov AG. The Mathematical Structure of Information Bottleneck Methods. Entropy. 2012; 14(3):456-479.

Chicago/Turabian Style

Gedeon, Tomáš; Parker, Albert E.; Dimitrov, Alexander G. 2012. "The Mathematical Structure of Information Bottleneck Methods." Entropy 14, no. 3: 456-479.

Entropy EISSN 1099-4300 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert