Causal Discovery and Forecasting in Nonstationary Environments with State-Space Models
This addresses the challenge of analyzing nonstationary time series in fields like economics and neuroscience, offering a method that integrates causal discovery with forecasting, though it appears incremental by building on existing state-space model approaches.
The paper tackled causal discovery and forecasting for nonstationary time series by using state-space models, showing that nonstationarity aids in identifying causal structure and improves forecasting, with experimental validation on synthetic and real-world datasets.
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 time-varying 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.