Embracing Discrete Search: A Reasonable Approach to Causal Structure Learning
This work addresses causal discovery for researchers and practitioners by offering a faster and more accurate method, though it is incremental as it builds on prior discrete search approaches.
The authors tackled the problem of causal structure learning by introducing FLOP, a score-based algorithm for linear models that uses fast parent selection and iterative Cholesky-based updates to reduce run-times, enabling effective discrete search and achieving near-perfect recovery in standard benchmarks.
We present FLOP (Fast Learning of Order and Parents), a score-based causal discovery algorithm for linear models. It pairs fast parent selection with iterative Cholesky-based score updates, cutting run-times over prior algorithms. This makes it feasible to fully embrace discrete search, enabling iterated local search with principled order initialization to find graphs with scores at or close to the global optimum. The resulting structures are highly accurate across benchmarks, with near-perfect recovery in standard settings. This performance calls for revisiting discrete search over graphs as a reasonable approach to causal discovery.