2015/06/30 by Shaohua Li, Li, Shaohua
Biochemistry, Genetics and Molecular Biology · Computer Science · Mathematics · #Bayesian Methods and Mixture Models #FOS: Computer and information sciences #Genetic and phenotypic traits in livestock #Machine Learning (stat.ML) #Statistical Methods and Inference
paper · pdf · doi:10.48550/arxiv.1506.09068
openalex publication_date 2015/06/30 · openalex created_date 2016/06/24 · openalex updated_date 2026/07/28
Factorized Information Criterion (FIC) is a recently developed information criterion, based on which a novel model selection methodology, namely Factorized Asymptotic Bayesian (FAB) Inference, has been developed and successfully applied to various hierarchical Bayesian models. The Dirichlet Process (DP) prior, and one of its well known representations, the Chinese Restaurant Process (CRP), derive another line of model selection methods. FIC can be viewed as a prior distribution over the latent variable configurations. Under this view, we prove that when the parameter dimensionality Dc=2, FIC is equivalent to CRP. We argue that when Dc>2, FIC avoids an inherent problem of DP/CRP, i.e. the data likelihood will dominate the impact of the prior, and thus the model selection capability will weaken as Dc increases. However, FIC overestimates the data likelihood. As a result, FIC may be overly biased towards models with less components. We propose a natural generalization of FIC, which finds a middle ground between CRP and FIC, and may yield more accurate model selection results than FIC.