A First Approach to Closeness Distributions

Probabilistic graphical models allow us to encode a large probability distribution as composition of smaller ones. It is oftentimes the case that we are interested in incorporating model idea some these distributions likely be similar one another. In this paper provide an information geometric approach on how incorporate and see it allows reinterpret already existing models. Our proposal relies providing formal definition what means close. We example can actioned for multinomial distributions. use results two hierarchical terms closeness