Scalable Variational Causal Discovery Unconstrained by Acyclicity
This addresses a bottleneck in causal inference for researchers by enabling more efficient uncertainty quantification over causal structures.
The paper tackles the challenge of efficient DAG sampling in Bayesian causal discovery by proposing a scalable variational method that generates acyclic graphs without explicit constraints, achieving superior performance on simulated and real datasets compared to state-of-the-art baselines.
Bayesian causal discovery offers the power to quantify epistemic uncertainties among a broad range of structurally diverse causal theories potentially explaining the data, represented in forms of directed acyclic graphs (DAGs). However, existing methods struggle with efficient DAG sampling due to the complex acyclicity constraint. In this study, we propose a scalable Bayesian approach to effectively learn the posterior distribution over causal graphs given observational data thanks to the ability to generate DAGs without explicitly enforcing acyclicity. Specifically, we introduce a novel differentiable DAG sampling method that can generate a valid acyclic causal graph by mapping an unconstrained distribution of implicit topological orders to a distribution over DAGs. Given this efficient DAG sampling scheme, we are able to model the posterior distribution over causal graphs using a simple variational distribution over a continuous domain, which can be learned via the variational inference framework. Extensive empirical experiments on both simulated and real datasets demonstrate the superior performance of the proposed model compared to several state-of-the-art baselines.