Measurement Dependence Inducing Latent Causal Models
This work addresses causal inference challenges in complex systems with latent variables, though it appears incremental by connecting to existing graph theory concepts.
The paper tackles the problem of causal structure learning for measurement dependence inducing latent (MeDIL) causal models by framing it as an edge clique cover problem, resulting in a non-parametric algorithm that returns minimal models without requiring linearity or Gaussianity assumptions.
We consider the task of causal structure learning over measurement dependence inducing latent (MeDIL) causal models. We show that this task can be framed in terms of the graph theoretic problem of finding edge clique covers,resulting in an algorithm for returning minimal MeDIL causal models (minMCMs). This algorithm is non-parametric, requiring no assumptions about linearity or Gaussianity. Furthermore, despite rather weak assumptions aboutthe class of MeDIL causal models, we show that minimality in minMCMs implies some rather specific and interesting properties. By establishing MeDIL causal models as a semantics for edge clique covers, we also provide a starting point for future work further connecting causal structure learning to developments in graph theory and network science.