复杂泛函的近似极大化子
Approximate maximizers of intricacy functionals
摘要:
G. Edelman,O. Sporns和G.托诺尼在理论生物学中引入了一个随机变量家族的神经复杂性。该泛函是复杂性的一个特例,即,子系统的互信息的平均值,其权重具有良好的数学特性。而且,它的最大值随着系统的规模以一定的速度增长。在这项工作中,我们计算正是这种增长速度的“近似极大化”的熵条件。这些近似最大化器同时适用于所有复杂性。我们还建立了一些性质的任意近似最大化,特别是存在一个阈值的大小的子系统的近似最大化:大多数较小的子系统几乎是等分布的,大多数较大的子系统确定整个系统。主要思想是随机构造具有高统计对称性的几乎最大化器,并考虑熵分布,即,给定大小的子系统的平均熵。后者引出了概率论和信息论的有趣问题。
英文摘要:
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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。