Interesting Papers in NIPS 2008

  1. E. Sudderth, M. Jordan. Shared Segmentation of Natural Scenes Using Dependent Pitman-Yor Processes.
    I am interested in how Pitman-Yor process is able to model power-lay data.

  2. Amit Gruber, Michal Rosen-Zvi and Yair Weiss. Latent Topic Models for Hypertext.
    Topic model describes the generation of hyperlinks between document pairs.
  3. Simon Lacoste-Julien, Fei Sha and Michael I. Jordan. DiscLDA: Discriminative Learning for
    Dimensionality Reduction and Classification
    .
    I am not yet quiet clear with how the linear translations were introduced in this Bayesian modeling approach.