Active Invariant Causal Prediction: Experiment Selection through Stability
This work addresses the challenge of costly experiments in causal inference by improving intervention selection, but it appears incremental as it builds on existing methods like ICP.
The authors tackled the problem of selecting optimal interventions for causal learning by proposing an active learning framework (A-ICP) based on Invariant Causal Prediction, which quickly identifies direct causes of a response variable while controlling error. They empirically analyzed the performance of their policies in population and finite-regime experiments, though no concrete numbers were provided in the abstract.
A fundamental difficulty of causal learning is that causal models can generally not be fully identified based on observational data only. Interventional data, that is, data originating from different experimental environments, improves identifiability. However, the improvement depends critically on the target and nature of the interventions carried out in each experiment. Since in real applications experiments tend to be costly, there is a need to perform the right interventions such that as few as possible are required. In this work we propose a new active learning (i.e. experiment selection) framework (A-ICP) based on Invariant Causal Prediction (ICP) (Peters et al., 2016). For general structural causal models, we characterize the effect of interventions on so-called stable sets, a notion introduced by (Pfister et al., 2019). We leverage these results to propose several intervention selection policies for A-ICP which quickly reveal the direct causes of a response variable in the causal graph while maintaining the error control inherent in ICP. Empirically, we analyze the performance of the proposed policies in both population and finite-regime experiments.