VC dimension and inner product space induced by Bayesian networks

Bayesian networks are graphical tools used to represent a high-dimensional probability distribution. They are used frequently in machine learning and many applications such as medical science. This paper studies whether the concept classes induced by a Bayesian network can be embedded into a low-dimensional inner product space. We focus on two-label classification tasks over the Boolean domain. For full Bayesian networks and almost full Bayesian networks with n variables, we show that VC dimension and the minimum dimension of the inner product space induced by them are 2^n-1. Also, for each Bayesian network N we show that VCdim(N)=Edim(N)=2^n^-^1+2^i if the network N^' constructed from N by removing X"n satisfies either (i) N^' is a full Bayesian network with n-1 variables, i is the number of parents of X"n, and i