Huang Biwei, Zhang Kun, Gong Mingming, Glymour Clark
Department of Philosophy, Carnegie Mellon University, Pittsburgh.
Department of Biomedical Informatics, University of Pittsburgh, Pittsburgh.
Proc Mach Learn Res. 2019 Jun;97:2901-2910.
In many scientific fields, such as economics and neuroscience, we are often faced with nonstationary time series, and concerned with both finding causal relations and forecasting the values of variables of interest, both of which are particularly challenging in such nonstationary environments. In this paper, we study causal discovery and forecasting for nonstationary time series. By exploiting a particular type of state-space model to represent the processes, we show that nonstationarity helps to identify causal structure and that forecasting naturally benefits from learned causal knowledge. Specifically, we allow changes in both causal strengths and noise variances in the nonlinear state-space models, which, interestingly, renders both the causal structure and model parameters identifiable. Given the causal model, we treat forecasting as a problem in Bayesian inference in the causal model, which exploits the timevarying property of the data and adapts to new observations in a principled manner. Experimental results on synthetic and real-world data sets demonstrate the efficacy of the proposed methods.
在许多科学领域，如经济学和神经科学，我们经常面临非平稳时间序列，并且关注寻找因果关系和预测感兴趣变量的值，而在这种非平稳环境中，这两者都极具挑战性。在本文中，我们研究非平稳时间序列的因果发现和预测。通过利用一种特定类型的状态空间模型来表示这些过程，我们表明非平稳性有助于识别因果结构，并且预测自然会从学到的因果知识中受益。具体而言，我们允许非线性状态空间模型中的因果强度和噪声方差发生变化，有趣的是，这使得因果结构和模型参数均可识别。给定因果模型，我们将预测视为因果模型中的贝叶斯推断问题，该问题利用数据的时变特性并以原则性方式适应新的观测值。在合成数据集和真实世界数据集上的实验结果证明了所提方法的有效性。
