Augment-and-conquer negative binomial processes

Mingyuan Zhou, Lawrence Carin

Research output: Chapter in Book/Report/Conference proceedingConference contribution

26 Scopus citations

Abstract

By developing data augmentation methods unique to the negative binomial (NB) distribution, we unite seemingly disjoint count and mixture models under the NB process framework. We develop fundamental properties of the models and derive efficient Gibbs sampling inference. We show that the gamma-NB process can be reduced to the hierarchical Dirichlet process with normalization, highlighting its unique theoretical, structural and computational advantages. A variety of NB processes with distinct sharing mechanisms are constructed and applied to topic modeling, with connections to existing algorithms, showing the importance of inferring both the NB dispersion and probability parameters.
Original languageEnglish (US)
Title of host publicationAdvances in Neural Information Processing Systems
Pages2546-2554
Number of pages9
StatePublished - Dec 1 2012
Externally publishedYes

Fingerprint

Dive into the research topics of 'Augment-and-conquer negative binomial processes'. Together they form a unique fingerprint.

Cite this