Factorization, Inference and Parameter Learning in Discrete AMP Chain Graphs
This work solves computational and interpretability issues for researchers using AMP chain graphs in probabilistic modeling.
The paper addresses computational barriers to using AMP chain graphs by developing factorization methods for discrete probability distributions that satisfy AMP independencies, enabling efficient inference and parameter learning through adaptation of existing algorithms for Markov and Bayesian networks.
We address some computational issues that may hinder the use of AMP chain graphs in practice. Specifically, we show how a discrete probability distribution that satisfies all the independencies represented by an AMP chain graph factorizes according to it. We show how this factorization makes it possible to perform inference and parameter learning efficiently, by adapting existing algorithms for Markov and Bayesian networks. Finally, we turn our attention to another issue that may hinder the use of AMP CGs, namely the lack of an intuitive interpretation of their edges. We provide one such interpretation.