Causal Discovery and Forecasting in Nonstationary Environments with State-Space Models
Causal Discovery and Forecasting in Nonstationary Environments with State-Space Models
复制标题
DOI：
--
复制
发表时间：
2019-05
期刊：
影响因子：
--
通讯作者：
Biwei Huang;Kun Zhang;Mingming Gong;C. Glymour
中科院分区：
文献类型：
--
作者：
Biwei Huang;Kun Zhang;Mingming Gong;C. Glymour
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，并关注寻找因果关系和预测感兴趣的变量的值，这两者在这种非平稳环境中特别具有挑战性。本文研究了非平稳时间序列的因果发现和预测问题。通过利用一种特定类型的状态空间模型来表示的过程中，我们表明，非平稳性有助于确定因果结构和预测自然受益于学习的因果知识。具体来说，我们允许在因果强度和噪声方差的非线性状态空间模型，有趣的是，使因果结构和模型参数可识别的变化。给定因果模型，我们将预测视为因果模型中贝叶斯推理的问题，该模型利用数据的时变特性并以原则性的方式适应新的观测。合成和真实世界的数据集上的实验结果表明，所提出的方法的有效性。
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.