Approximate maximizers of intricacy functionals

DOI10.1007/S00440-011-0350-YMaRDI QIDQ714956zbMATH OpenOpenAlexFDO

Authors Jérôme Buzzi, L. Zambotti

Publication date 12 October 2012

Published in Zeitschrift für Wahrscheinlichkeitstheorie und Verwandte Gebiete (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/0909.2120

zbMATH Keywords

discrete probabilityentropyintricacymaximizationneural complexity of a family of random variables

Mathematics Subject Classification ID

Combinatorial probability (60C05) Systems biology, networks (92C42) Measures of information, entropy (94A17)

Abstract: G. Edelman, O. Sporns, and G. Tononi introduced in theoretical biology the neural complexity of a family of random variables. This functional is a special case of intricacy, i.e., an average of the mutual information of subsystems whose weights have good mathematical properties. Moreover, its maximum value grows at a definite speed with the size of the system. In this work, we compute exactly this speed of growth by building "approximate maximizers" subject to an entropy condition. These approximate maximizers work simultaneously for all intricacies. We also establish some properties of arbitrary approximate maximizers, in particular the existence of a threshold in the size of subsystems of approximate maximizers: most smaller subsystems are almost equidistributed, most larger subsystems determine the full system. The main ideas are a random construction of almost maximizers with a high statistical symmetry and the consideration of entropy profiles, i.e., the average entropies of sub-systems of a given size. The latter gives rise to interesting questions of probability and information theory.

Recommendations

• Mean mutual information and symmetry breaking for finite random fields
• Dynamical intricacy and average sample complexity
• How should complexity scale with system size?
• Factorized mutual information maximization.
• Dynamical intricacy and average sample complexity for random bundle transformations

Cites work

• A new class of non-Shannon-type inequalities for entropies
• Analytical description of the evolution of neural networks: Learning rules and complexity
• Elements of Information Theory
• scientific article; zbMATH DE number 2021774 (Why is no real title available?)
• Information, Physics, and Computation
• Mean mutual information and symmetry breaking for finite random fields
• The maximal probability that k-wise independent bits are all 1

Cited in

(7)

• Dynamical intricacy and average sample complexity of amenable group actions
• Mean mutual information and symmetry breaking for finite random fields
• Dynamical intricacy and average sample complexity for random bundle transformations
• Dynamical intricacy and average sample complexity
• Factorized mutual information maximization.
• The pressure of intricacy and average sample complexity for amenable group actions
• Local intricacy and average sample complexity for amenable group actions

This page was built for publication: Approximate maximizers of intricacy functionals

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q714956)