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 1102.2684cs.ITcs.CVcs.IRmath.IT
收藏

指数族的信息

Chernoff information of exponential families

Sony Computer Science Laboratories(索尼计算机科学实验室);École Polytechnique(巴黎综合理工学院)

Frank Nielsen

摘要:

对于$2$类分类问题,最优贝叶斯决策规则的错误概率的上界是无信息的。然而,事实证明,在实践中,很难计算甚至近似的Beschoff界限。在统计学中,许多常见的分布,如高斯分布,泊松分布或称为多项式的频率直方图,都可以在指数族的统一框架中处理。在这份说明中,我们证明了相同的指数家族的成员的Beschoff信息可以解析地导出在封闭的形式,或有效地近似使用一个简单的测地二分法优化技术的基础上的“Beschoff点”的基本统计流形上的精确几何表征。

英文摘要:

Chernoff information upper bounds the probability of error of the optimal Bayesian decision rule for $2$-class classification problems. However, it turns out that in practice the Chernoff bound is hard to calculate or even approximate. In statistics, many usual distributions, such as Gaussians, Poissons or frequency histograms called multinomials, can be handled in the unified framework of exponential families. In this note, we prove that the Chernoff information for members of the same exponential family can be either derived analytically in closed form, or efficiently approximated using a simple geodesic bisection optimization technique based on an exact geometric characterization of the "Chernoff point" on the underlying statistical manifold.

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。

↑