arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2410.16004math.STmath.PRstat.MLstat.TH
收藏

贝叶斯网络是否通常是忠实的?

Are Bayesian networks typically faithful?

VU Amsterdam(阿姆斯特丹自由大学);Korteweg-de Vries Institute for Mathematics, University of Amsterdam(阿姆斯特丹大学科特维格-德弗里斯数学研究所)

Philip Boeken, Patrick Forré, Joris M. Mooij

AI总结:

研究证明贝叶斯网络在特定条件下忠实性构成开放密集集,扩展了线性高斯和离散网络的结果,并表明基于约束的因果发现算法在典型网络集上一致。

摘要:

忠实性是因果推断中常见的假设,通常受到线性高斯和离散贝叶斯网络的忠实参数通常是典型这一事实的推动,以及 folklore 的信念,即这种假设也应适用于其他类型的贝叶斯网络。我们通过证明,在给定的DAG上所有贝叶斯网络中,忠实的贝叶斯网络确实构成了一个密集且开放的集合,以总变分度量为标准。这并不直接表明在统计应用中常考虑的受限类别的贝叶斯网络中忠实性是典型的。为此,我们考虑了由条件指数族参数化的贝叶斯网络,证明在正则条件下,忠实参数构成一个密集且开放的集合,而不忠实参数具有勒贝格测度为零,诱导的忠实分布在弱拓扑下是开放且密集的。这扩展了线性高斯和离散贝叶斯网络的现有结果。我们还展示了非参数类的贝叶斯网络,其条件密度具有均匀连续和均匀有界的条件密度时,忠实的贝叶斯网络在弱拓扑下是开放且密集的。所有这些结果也适用于具有潜在变量的贝叶斯网络,只要忠实性仅针对潜在投影要求。最后,对于考虑的条件指数族参数化和非参数条件密度模型,条件独立性的拓扑性质保证了条件独立性测试的一致性。结合忠实性的拓扑性质,这表明像PC和FCI这样的可靠基于约束的因果发现算法在开放且密集——即“典型”的——贝叶斯网络集上是自洽的。

英文摘要:

Faithfulness is a common assumption in causal inference, often motivated by the fact that the faithful parameters of linear Gaussian and discrete Bayesian networks are typical, and the folklore belief that this should also hold for other classes of Bayesian networks. We address this open question by showing that among all Bayesian networks over a given DAG, the faithful Bayesian networks are indeed `typical': they constitute a dense, open set with respect to the total variation metric. This does not directly imply that faithfulness is typical in restricted classes of Bayesian networks that are often considered in statistical applications. To this end we consider the class of Bayesian networks parametrised by conditional exponential families, for which we show that under regularity conditions, the faithful parameters constitute a dense and open set, the unfaithful parameters have Lebesgue measure zero, and the induced faithful distributions are open and dense in the weak topology. This extends the existing results for linear Gaussian and discrete Bayesian networks. We also show for nonparametric classes of Bayesian networks with uniformly equicontinuous and uniformly bounded conditional densities that the faithful Bayesian networks are open and dense in the weak topology. All these results also hold for Bayesian networks with latent variables, if faithfulness is only required to hold with respect to the latent projection. Finally, for the considered conditional exponential family parametrisations and nonparametric conditional density models, the topological properties of conditional independence imply the existence of a consistent conditional independence test. Together with the topological properties of faithfulness, this implies that sound constraint-based causal discovery algorithms like PC and FCI are consistent on an open and dense -- and hence `typical' -- set of Bayesian networks.

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。

↑