arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.04667stat.MEcs.LG
收藏

随机矩阵的直径:贝叶斯网络敏感性分析的一种新度量

The diameter of a stochastic matrix: A new measure for sensitivity analysis in Bayesian networks

School of Science and Technology, IE University(IE大学科学技术学院);University of Warwick(华威大学);The Alan Turing Institute(艾伦·图灵研究所)

Manuele Leonelli, Jim Q. Smith, Sophia K. Wright

AI总结:

本文提出用全变差距离和新的“直径”度量刻画贝叶斯网络中条件概率表的依赖强度,为模型误设提供更简单、可证明且透明的稳健性界,并将其融入贝叶斯网络构建。

摘要:

贝叶斯网络因其可解释性以及在纳入异构信息方面的灵活性,成为风险管理和决策支持中应用最广泛的概率模型类别之一。在任何应用建模中,评估关于某些目标变量的推断对模型变化的稳健程度都至关重要。在贝叶斯网络中,这类分析属于敏感性分析的范畴,通常通过使用Kullback-Leibler信息度量来量化差异。本文认为,基于人们熟悉的全变差距离的稳健性方法,能够为模型误设的稳健性提供更简单且更有价值的界,这些界既在形式上可证明合理,又具有透明性。我们引入一种新的条件概率表中的依赖性度量,称为直径,用以推导此类界。该度量量化了一个变量与其父变量之间的依赖强度。我们展示了如何将这种形式化的稳健性考量嵌入到贝叶斯网络的构建过程中。

英文摘要:

Bayesian networks are one of the most widely used classes of probabilistic models for risk management and decision support because of their interpretability and flexibility in including heterogeneous pieces of information. In any applied modelling, it is critical to assess how robust the inferences on certain target variables are to changes in the model. In Bayesian networks, these analyses fall under the umbrella of sensitivity analysis, which is most commonly carried out by quantifying dissimilarities using Kullback-Leibler information measures. In this paper, we argue that robustness methods based instead on the familiar total variation distance provide simple and more valuable bounds on robustness to misspecification, which are both formally justifiable and transparent. We introduce a novel measure of dependence in conditional probability tables called the diameter to derive such bounds. This measure quantifies the strength of dependence between a variable and its parents. We demonstrate how such formal robustness considerations can be embedded in building a Bayesian network.

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。

↑