Learning Graphical Models over partial k-trees

We show that the class of strongly connected graphical models with tree-width at most k can be properly efficiently PAC-learnt with respect to the Kullback-Leibler Divergence. Previous approaches to this problem, such as those of Chow ([1]), and Hoffgen ([7]) have shown that this class is PAC-learnable (though not necessarily efficiently unless k = 1) by reducing to a NP-complete combinatorial optimization problem. Unless P=NP, these approaches will take exponential amounts of time. Our approach differs significantly from these, in that it first attempts to find approximate conditional independencies by solving (polynomially many) submodular optimization problems, and then using a dynamic programming formulation to combine the approximate conditional independence information to derive a graphical model with underlying graph of the tree-width specified. This gives us an efficient (polynomial time) PAC-learning algorithm which requires only polynomial number of samples of the true distribution, and only polynomial running time.