Dependent nonparametric trees for dynamic hierarchical clustering: Supplementary material

There exist a wide variety of distributions over trees with infinitely many nodes, including the nested Chinese restaurant process (Blei et al., 2004), the Dirichlet diffusion tree (Neal, 2003), and Kingman’s coalescent (Kingman, 1982). These models differ from the TSSBP in that data can only be associated with a leaf node, or equivalently a full path from root to leaf. We chose to base our clustering model on the TSSBP because, in many applications, it makes sense to associate data with internal nodes. For example, a document may be narrowly about Physics or Biology, or may be a more broad article on the sciences in general.