Beta Diffusion Trees

We define the beta diffusion tree, a random tree structure with a set of leaves that defines a collec-tion of overlapping subsets of objects, known as a feature allocation. The generative process for the tree is defined in terms of particles (representing the objects) diffusing in some continuous space, analogously to the Dirichlet and Pitman–Yor dif-fusion trees (Neal, 2003b; Knowles & Ghahra-mani, 2011), both of which define tree structures over clusters of the particles. With the beta diffu-sion tree, however, multiple copies of a particle may exist and diffuse to multiple locations in the continuous space, resulting in (a random number of) possibly overlapping clusters of the objects. We demonstrate how to build a hierarchically-clustered factor analysis model with the beta dif-fusion tree and how to perform inference over the random tree structures with a Markov chain Monte Carlo algorithm. We conclude with sev-eral numerical experiments on missing data prob-lems with data sets of gene expression arrays, international development statistics, and intrana-tional socioeconomic measurements. 1