Testing Directed Acyclic Graph via Structural, Supervised and Generative Adversarial Learning
Testing Directed Acyclic Graph via Structural, Supervised and Generative Adversarial Learning
复制标题
DOI：
10.1080/01621459.2023.2220169
复制
发表时间：
2021-06
期刊：
影响因子：
--
通讯作者：
C. Shi;Yunzhe Zhou;Lexin Li
中科院分区：
文献类型：
--
作者：
C. Shi;Yunzhe Zhou;Lexin Li
本文提出了一种新的有向无环图（DAG）假设检验方法。虽然有丰富的DAG估计方法，但DAG推理解决方案相对较少。此外，现有方法往往强加一些特定的模型结构，如线性模型或加性模型，并假设独立的数据观测值。相反，我们提出的测试允许随机变量之间的关联是非线性的，数据是时间相关的。我们基于一些高度灵活的神经网络学习器来构建测试。我们建立了检验的渐近保证，同时允许每个受试者的数量或时间点的数量发散到无穷大。我们通过模拟和大脑连接网络分析证明了该测试的有效性。
In this article, we propose a new hypothesis testing method for directed acyclic graph (DAG). While there is a rich class of DAG estimation methods, there is a relative paucity of DAG inference solutions. Moreover, the existing methods often impose some specific model structures such as linear models or additive models, and assume independent data observations. Our proposed test instead allows the associations among the random variables to be nonlinear and the data to be time-dependent. We build the test based on some highly flexible neural networks learners. We establish the asymptotic guarantees of the test, while allowing either the number of subjects or the number of time points for each subject to diverge to infinity. We demonstrate the efficacy of the test through simulations and a brain connectivity network analysis.