Chong Wang will present his preFPO on Wednesday November 7 at 1PM in Room 302 (note room!). The members of his committee are: David Blei, advisor; Rob Schapire and Eric Xing (CMU), readers; Christiane Fellbaum and Andrea LaPaugh, readers. Everyone is invited to attend his talk. His abstract follows below. -------------------------- Title: Hierarchical Bayesian modeling: models and inference algorithms Hierarchical Bayesian models have become a popular tool for analyzing large-scale real-world data, such as text and images. Through these models, people can build useful tools for latent structure discovery, browsing and recommendations. In this talk, I will present several recent advances in the area of hierarchical Bayesian modeling, with an emphasis on topic modeling, Bayesian nonparametrics and approximate posterior inference. Specifically, I will talk about a novel model on recommending scientific articles that provides an interpretable latent structure for both users and items in a recommender system and then present an online variational inference algorithm that scales up to millions of articles on a single machine and also does model selection. Finally, I will summarize with some ongoing work.