Efficient Identification of Direct Causal Parents via Invariance and Minimum Error Testing
This work addresses the challenge of scaling causal discovery to large problems for researchers and practitioners, though it is incremental as it builds on existing ICP methods.
The paper tackles the inefficiency and identifiability limitations of Invariant Causal Prediction (ICP) for finding direct causal parents by proposing MMSE-ICP and fastICP, which use an error inequality to reduce the number of tests and improve performance, achieving state-of-the-art results on a large-scale real data benchmark.
Invariant causal prediction (ICP) is a popular technique for finding causal parents (direct causes) of a target via exploiting distribution shifts and invariance testing (Peters et al., 2016). However, since ICP needs to run an exponential number of tests and fails to identify parents when distribution shifts only affect a few variables, applying ICP to practical large scale problems is challenging. We propose MMSE-ICP and fastICP, two approaches which employ an error inequality to address the identifiability problem of ICP. The inequality states that the minimum prediction error of the predictor using causal parents is the smallest among all predictors which do not use descendants. fastICP is an efficient approximation tailored for large problems as it exploits the inequality and a heuristic to run fewer tests. MMSE-ICP and fastICP not only outperform competitive baselines in many simulations but also achieve state-of-the-art result on a large scale real data benchmark.