Practical collapsed variational bayes inference for hierarchical dirichlet process
Issei Sato, Kenichi Kurihara, Hiroshi Nakagawa · 2012
We propose a novel collapsed variational Bayes (CVB) inference for the hierarchical Dirichlet process (HDP). While the existing CVB inference for the HDP variant of latent Dirichlet allocation (LDA) is more complicated and harder to implement than that for LDA, the proposed algorithm is simple to implement, does not require variance counts to be maintained, does not need to set hyper-parameters, and has good predictive performance.