Preprint
Sep 2026
Gibbs Sampling for Bayesian Generalized Poisson Matrix Factorization
A Bayesian extension of GPMF, referred to as Bayesian GPMF, is proposed, and an infinite mixture representation of the exponentially tilted beta (EBeta) distribution is derived and a finite approximation based on this representation is developed.
F. Sakaori, Hiroyasu Abe
· 0 citations