Probabilistic Active Learning of Functions in Structural Causal Models
This addresses a specific step in causal inference for researchers, but appears incremental as it builds on established causal discovery methods.
The paper tackles the problem of learning functions in Structural Causal Models after causal graph identification, proposing a probabilistic active learning scheme that selects optimally informative interventions. It demonstrates that this approach produces structured exploration policies that significantly outperform unstructured baselines in simple examples.
We consider the problem of learning the functions computing children from parents in a Structural Causal Model once the underlying causal graph has been identified. This is in some sense the second step after causal discovery. Taking a probabilistic approach to estimating these functions, we derive a natural myopic active learning scheme that identifies the intervention which is optimally informative about all of the unknown functions jointly, given previously observed data. We test the derived algorithms on simple examples, to demonstrate that they produce a structured exploration policy that significantly improves on unstructured base-lines.