Differentiable DAG Sampling
This addresses the challenge of efficient and valid DAG learning for causal inference, representing an incremental improvement over existing differentiable methods.
The paper tackles the problem of learning directed acyclic graphs (DAGs) from observational data by proposing VI-DP-DAG, a differentiable probabilistic model that combines DAG sampling with variational inference, resulting in improved DAG structure and causal mechanism learning with faster training than competitors.
We propose a new differentiable probabilistic model over DAGs (DP-DAG). DP-DAG allows fast and differentiable DAG sampling suited to continuous optimization. To this end, DP-DAG samples a DAG by successively (1) sampling a linear ordering of the node and (2) sampling edges consistent with the sampled linear ordering. We further propose VI-DP-DAG, a new method for DAG learning from observational data which combines DP-DAG with variational inference. Hence,VI-DP-DAG approximates the posterior probability over DAG edges given the observed data. VI-DP-DAG is guaranteed to output a valid DAG at any time during training and does not require any complex augmented Lagrangian optimization scheme in contrast to existing differentiable DAG learning approaches. In our extensive experiments, we compare VI-DP-DAG to other differentiable DAG learning baselines on synthetic and real datasets. VI-DP-DAG significantly improves DAG structure and causal mechanism learning while training faster than competitors.