arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1008.0817physics.data-anq-bio.QM
收藏

互信息的下界

Lower Bounds on Mutual Information

David V. Foster, Peter Grassberger

摘要:

本文修正了A中关于实值随机变量间互信息下界的结论。Kraskov { \it等人},E { \bf 69},066138(2004)。我们表明,非平凡的下限MI的线性相关依赖于边际(单变量)分布。这是如此,尽管MI的不变性下重新参数化,因为线性相关性不是不变的。最简单的界限得到高斯,但最有趣的实用目的是获得均匀的边缘分布。后者一般可以通过使用单个变量的秩而不是它们的实际值来执行,在这种情况下,人们可以根据斯皮尔曼相关系数获得MI的界限。我们与基因表达数据表明,这些界限一般是非平凡的,其(非)饱和度产生有价值的见解。

英文摘要:

We correct claims about lower bounds on mutual information (MI) between real-valued random variables made in A. Kraskov {\it et al.}, Phys. Rev. E {\bf 69}, 066138 (2004). We show that non-trivial lower bounds on MI in terms of linear correlations depend on the marginal (single variable) distributions. This is so in spite of the invariance of MI under reparametrizations, because linear correlations are not invariant under them. The simplest bounds are obtained for Gaussians, but the most interesting ones for practical purposes are obtained for uniform marginal distributions. The latter can be enforced in general by using the ranks of the individual variables instead of their actual values, in which case one obtains bounds on MI in terms of Spearman correlation coefficients. We show with gene expression data that these bounds are in general non-trivial, and the degree of their (non-)saturation yields valuable insight.

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。

↑