Comments on Approximating Discrete Probability Distributions with Dependence Trees

Chow and Liu introduced the notion of tree dependence to approximate a kth order probability distribution. More recently, Wong and Wang proposed a different product approximation. The aim of this paper is to show that the tree dependence approximation suggested by Chow and Liu can be derived by minimizing an upper bound of the Bayes error rate under certain assumptions. It is also shown that the method proposed by Wong and Wang does not necessarily lead to fewer misclassifications because it is a special case of such a minimization procedure.