arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.00623stat.MLcs.LGstat.ME
收藏

基于高斯过程网络的贝叶斯因果推断

Bayesian Causal Inference with Gaussian Process Networks

University of Basel(巴塞尔大学);ETH Zurich(苏黎世联邦理工学院);University College London(伦敦大学学院)

Enrico Giudice, Jack Kuipers, Giusi Moffa

AI总结:

本文提出在Gaussian Process Network模型中进行贝叶斯因果推断,通过模拟干预效应传播及局部变量近似方法,结合MCMC处理结构不确定性,能准确识别非线性数据中的干预效应。

摘要:

从观测数据中进行因果发现和推断是统计学中的一个重要问题,在建模和计算上都存在挑战。这些问题通常通过对联合分布施加严格的假设(如线性)来解决。我们考虑在Gaussian Process Network (GPN)(高斯过程网络)模型中对假设干预的效应进行贝叶斯估计的问题,这是一种灵活的因果框架,允许非参数地描述因果关系。我们详细说明了如何通过在整个网络中模拟干预效应并将干预效应传播到下游变量,来对GPN执行因果推断。我们进一步推导出一种更简单的计算近似方法,即仅将干预分布估计为局部变量的函数,并通过加性高斯过程对条件分布进行建模。我们将这两个框架扩展到已知因果图之外的情况,通过马尔可夫链蒙特卡洛方法纳入对因果结构的不确定性。模拟研究表明,我们的方法能够识别非高斯、非线性观测数据中假设干预的效应,并准确反映因果估计的后验不确定性。最后,我们在A. thaliana基因表达数据集上,将基于GPN的因果推断方法的结果与现有方法进行了比较。

英文摘要:

Causal discovery and inference from observational data is an essential problem in statistics posing both modeling and computational challenges. These are typically addressed by imposing strict assumptions on the joint distribution such as linearity. We consider the problem of the Bayesian estimation of the effects of hypothetical interventions in the Gaussian Process Network (GPN) model, a flexible causal framework which allows describing the causal relationships nonparametrically. We detail how to perform causal inference on GPNs by simulating the effect of an intervention across the whole network and propagating the effect of the intervention on downstream variables. We further derive a simpler computational approximation by estimating the intervention distribution as a function of local variables only, modeling the conditional distributions via additive Gaussian processes. We extend both frameworks beyond the case of a known causal graph, incorporating uncertainty about the causal structure via Markov chain Monte Carlo methods. Simulation studies show that our approach is able to identify the effects of hypothetical interventions with non-Gaussian, non-linear observational data and accurately reflect the posterior uncertainty of the causal estimates. Finally we compare the results of our GPN-based causal inference approach to existing methods on a dataset of $A.~thaliana$ gene expressions.

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。

↑