arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.06197stat.MLcs.LGstat.APstat.ME
收藏

估计极值的有向树

Estimating a Directed Tree for Extremes

University of Texas at Austin(德克萨斯大学奥斯汀分校);Technical University of Munich(慕尼黑工业大学)

Ngoc Mai Tran, Johannes Buck, Claudia Klüppelberg

AI总结:

提出一种基于最大线性贝叶斯网络定性特征的新算法,从极值数据中估计根有向生成树,并在基准数据上表现优异,且证明其一致性。

摘要:

我们提出了一种从极值数据中估计根有向生成树的新方法。一个突出的例子是河流网络,它需要从一组站点测得的极端流量中发现。我们的新算法利用了最大线性贝叶斯网络的定性特征,该网络专为极值中的因果建模而设计。该算法估计双变量得分并返回一棵根有向生成树。它在基准数据和新数据上表现极佳。我们证明了新估计器在带噪声的最大线性贝叶斯网络模型下是一致的。我们还在一个小型模拟研究中评估了其优点和局限性。

英文摘要:

We propose a new method to estimate a root-directed spanning tree from extreme data. A prominent example is a river network, to be discovered from extreme flow measured at a set of stations. Our new algorithm utilizes qualitative aspects of a max-linear Bayesian network, which has been designed for modelling causality in extremes. The algorithm estimates bivariate scores and returns a root-directed spanning tree. It performs extremely well on benchmark data and new data. We prove that the new estimator is consistent under a max-linear Bayesian network model with noise. We also assess its strengths and limitations in a small simulation study.

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。

↑