Causal Forecasting:Generalization Bounds for Autoregressive Models
This work addresses the gap in understanding causal implications of forecasting methods, which is crucial for reliable predictions in fields like economics and healthcare, though it is incremental by building on existing causal learning theory.
The paper tackles the problem of causal generalization in forecasting, specifically how autoregressive models perform under interventions compared to observational data, and provides uniform convergence bounds for causal generalizability in VAR models, marking the first theoretical guarantees in this time-series setting.
Despite the increasing relevance of forecasting methods, causal implications of these algorithms remain largely unexplored. This is concerning considering that, even under simplifying assumptions such as causal sufficiency, the statistical risk of a model can differ significantly from its \textit{causal risk}. Here, we study the problem of \textit{causal generalization} -- generalizing from the observational to interventional distributions -- in forecasting. Our goal is to find answers to the question: How does the efficacy of an autoregressive (VAR) model in predicting statistical associations compare with its ability to predict under interventions? To this end, we introduce the framework of \textit{causal learning theory} for forecasting. Using this framework, we obtain a characterization of the difference between statistical and causal risks, which helps identify sources of divergence between them. Under causal sufficiency, the problem of causal generalization amounts to learning under covariate shifts, albeit with additional structure (restriction to interventional distributions under the VAR model). This structure allows us to obtain uniform convergence bounds on causal generalizability for the class of VAR models. To the best of our knowledge, this is the first work that provides theoretical guarantees for causal generalization in the time-series setting.