Reinforcement Learning for Causal Discovery without Acyclicity Constraints
This work addresses the problem of computational inefficiency in causal discovery for researchers and practitioners, offering a novel method that is incremental in improving exploration but not a paradigm shift.
The paper tackles the challenge of efficiently exploring the vast space of directed acyclic graphs (DAGs) in causal discovery by introducing ALIAS, a reinforcement learning method that generates DAGs in a single step with quadratic complexity, bypassing acyclicity constraints and showing strong performance compared to state-of-the-art methods on synthetic and real datasets.
Recently, reinforcement learning (RL) has proved a promising alternative for conventional local heuristics in score-based approaches to learning directed acyclic causal graphs (DAGs) from observational data. However, the intricate acyclicity constraint still challenges the efficient exploration of the vast space of DAGs in existing methods. In this study, we introduce ALIAS (reinforced dAg Learning wIthout Acyclicity conStraints), a novel approach to causal discovery powered by the RL machinery. Our method features an efficient policy for generating DAGs in just a single step with an optimal quadratic complexity, fueled by a novel parametrization of DAGs that directly translates a continuous space to the space of all DAGs, bypassing the need for explicitly enforcing acyclicity constraints. This approach enables us to navigate the search space more effectively by utilizing policy gradient methods and established scoring functions. In addition, we provide compelling empirical evidence for the strong performance of ALIAS in comparison with state-of-the-arts in causal discovery over increasingly difficult experiment conditions on both synthetic and real datasets.