Information Bottlenecks, Causal States, and Statistical Relevance Bases:
How to Represent Relevant Information in Memoryless Transduction

Cosma Rohilla Shalizi and James P. Crutchfield
Santa Fe Institute
1399 Hyde Park Rd.
Santa Fe, NM 87501, USA

Abstract

Discovering relevant, but possibly hidden, variables is a key step in constructing useful and predictive theories about the natural world. This brief note explains the connections between three approaches to this problem: the recently introduced information-bottleneck method, the computational mechanics approach to inferring optimal models, and Salmon's statistical relevance basis.

Citation

C. R. Shalizi and J. P. Crutchfield Information Bottlenecks, Causal States, and Statistical Relevance Bases: How to Represent Relevant Information in Memoryless Transduction, Santa Fe Insitute Working Paper 00-06-XXX. arXiv.org/abs/nlin.AO/0006025.

To transfer a compressed PostScript version of the paper
click on its title or use one of the links below.