Causal Temporal Regime Structure Learning
This addresses a key limitation for fields like economics and neuroscience by enabling causal analysis in non-stationary time series with changing structures, though it is an incremental advance building on existing causal discovery frameworks.
The paper tackles the problem of causal discovery in multivariate time series with sequential regimes, where existing methods assume stationarity, and presents CASTOR, a method that concurrently learns the number of regimes, their arrangement, and causal DAGs for each regime, showing consistent outperformance over existing models in detecting regimes and learning DAGs across linear and nonlinear settings on synthetic and real-world datasets.
Understanding causal relationships in multivariate time series is essential for predicting and controlling dynamic systems in fields like economics, neuroscience, and climate science. However, existing causal discovery methods often assume stationarity, limiting their effectiveness when time series consist of sequential regimes, consecutive temporal segments with unknown boundaries and changing causal structures. In this work, we firstly introduce a framework to describe and model such time series. Then, we present CASTOR, a novel method that concurrently learns the Directed Acyclic Graph (DAG) for each regime while determining the number of regimes and their sequential arrangement. CASTOR optimizes the data log-likelihood using an expectation-maximization algorithm, alternating between assigning regime indices (expectation step) and inferring causal relationships in each regime (maximization step). We establish the identifiability of the regimes and DAGs within our framework. Extensive experiments show that CASTOR consistently outperforms existing causal discovery models in detecting different regimes and learning their DAGs across various settings, including linear and nonlinear causal relationships, on both synthetic and real world datasets.