Constraint-based Causal Structure Learning when Faithfulness Fails Host Publication: Finds and Results from the Swedish Cyprus Expedition: A Gender Perspective at the Medelhavsmuseet Authors: J. Lemeire and K. Steenhaut Publication Year: 2009
Abstract: Constraint-based causal structure learning algorithms rely on the faithfulness property.
For faithfulness, all conditional independencies should come from the system's causal structure.
The problem is that even for linear Gaussian models the property is not tenable.
In this paper, we identify 4 non-causal properties that generate conditional independencies and investigate whether they can be recognized by patterns in the conditional independencies. External Link.
|