arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1712.09741cs.ITmath.IT
收藏

Gauss图间互信息的拓扑和代数性质

Topological and Algebraic Properties of Chernoff Information between Gaussian Graphs

Binglin Li, Shuangqing Wei, Yue Wang, Jian Yuan

摘要:

本文试图找出判别一组高斯图时,确定高斯信息的因素。我们发现两个高斯图的自相关信息可以由它们的协方差矩阵的广义特征值来确定。我们发现单位广义特征值不影响分类信息,其对应的维数不提供分类信息。此外,我们可以提供一个偏序之间的一系列独立嫁接操作连接的高斯树,使用的braffff信息。利用广义特征值与特征信息之间的关系,可以在最小信息损失的情况下进行最优线性降维。

英文摘要:

In this paper, we want to find out the determining factors of Chernoff information in distinguishing a set of Gaussian graphs. We find that Chernoff information of two Gaussian graphs can be determined by the generalized eigenvalues of their covariance matrices. We find that the unit generalized eigenvalue doesn't affect Chernoff information and its corresponding dimension doesn't provide information for classification purpose. In addition, we can provide a partial ordering using Chernoff information between a series of Gaussian trees connected by independent grafting operations. With the relationship between generalized eigenvalues and Chernoff information, we can do optimal linear dimension reduction with least loss of information for classification.

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。

↑