On the Intersection Property of Conditional Independence and its Application to Causal Discovery
It addresses a foundational problem in causal discovery for researchers, offering incremental improvements in identifiability conditions.
This work investigates the intersection property of conditional independence, providing necessary and sufficient conditions for it to hold under continuous density assumptions, and applies this to causal inference by enabling weaker conditions for identifying graphical structures in additive noise models.
This work investigates the intersection property of conditional independence. It states that for random variables $A,B,C$ and $X$ we have that $X$ independent of $A$ given $B,C$ and $X$ independent of $B$ given $A,C$ implies $X$ independent of $(A,B)$ given $C$. Under the assumption that the joint distribution has a continuous density, we provide necessary and sufficient conditions under which the intersection property holds. The result has direct applications to causal inference: it leads to strictly weaker conditions under which the graphical structure becomes identifiable from the joint distribution of an additive noise model.