Dagma-DCE: Interpretable, Non-Parametric Differentiable Causal Discovery
Daniel Waxman, Kurt Butler, Petar M. Djurić · IEEE Open Journal of Signal Processing · 2024
We introduceDagma-DCE, an interpretable and model-agnostic scheme for differentiable causal discovery. Current non- or over-parametric methods in differentiable causal discovery use opaque proxies of “independence” to justify the inclusion or exclusion of a causal relationship. We show theoretically and empirically that these proxies may be arbitrarily different than the actual causal strength. Juxtaposed with existing differentiable causal discovery algorithms,Dagma-DCEuses an interpretable measure of causal strength to define weighted adjacency matrices. In a number of simulated datasets, we show our method achieves state-of-the-art level performance. We additionally show thatDagma-DCEallows for principled thresholding and sparsity penalties by domain-experts. The code for our method is available open-source athttps://github.com/DanWaxman/DAGMA-DCE, and can easily be adapted to arbitrary differentiable models.