Problem
We now examine how to prove score equivalence for the BDe score. Assume that we have a prior specified by an equivalent sample size α and prior distribution P'. Prove the following:
a. Consider networks over the variables X and Y. Show that the BDe score of X → Y is equal to that of X ← Y.
b. Show that if G and G 0 are identical except for a covered edge reversal of X → Y, then the BDe score of both networks is equal.
c. Show that the proof of score equivalence follows from the last result and theorem.