Past-future information bottleneck in dynamical systems

Phys Rev E Stat Nonlin Soft Matter Phys. 2009 Apr;79(4 Pt 1):041925. doi: 10.1103/PhysRevE.79.041925. Epub 2009 Apr 27.

Abstract

Biological systems need to process information in real time and must trade off accuracy of presentation and coding costs. Here we operationalize this trade-off and develop an information-theoretic framework that selectively extracts information of the input past that is predictive about the output future, obtaining a generalized eigenvalue problem. Thereby, we unravel the input history in terms of structural phase transitions corresponding to additional dimensions of a state space. We elucidate the relation to canonical correlation analysis and give a numerical example. Altogether, this work relates information-theoretic optimization to the joint problem of system identification and model reduction.

Publication types

  • Research Support, Non-U.S. Gov't

MeSH terms

  • Algorithms
  • Forecasting*
  • Information Theory
  • Models, Biological*
  • Models, Theoretical*