arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1503.08844math.STstat.TH
收藏

广义过程的新Fréchet特征及相关的灵敏度指标

New Fréchet features for random distributions and associated sensitivity indices

Jean-Claude Fort, Thierry Klein

摘要:

在这篇文章中,我们定义了新的随机累积分布函数使用对比度的Fragchet功能。这些对比允许构建Wasserstein成本,并且我们的新功能使平均成本最小化,因为Fragchet均值使均方Wasserstein $_2$距离最小化。新特征的一个例子是中位数,更一般的是分位数。从这些定义,我们能够定义灵敏度指标时,广义过程是一个随机码的输出。与Fragchet相关联意味着我们扩展了Sobol指数,并且通常与我们先前提出的对比相关联的指数。

英文摘要:

In this article we define new FrÈchet features for random cumulative distribution functions using contrast. These contrasts allow to construct Wasserstein costs and our new features minimize the average costs as the FrÈchet mean minimizes the mean square Wasserstein$_2$ distance. An example of new features is the median, and more generally the quantiles. From these definitions, we are able to define sensitivity indices when the random distribution is the output of a stochastic code. Associated to the FrÈchet mean we extend the Sobol indices, and in general the indices associated to a contrast that we previously proposed.

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。

↑