A0992
Title: High-dimensional covariate-augmented overdispersed Poisson factor model
Authors: Qingzhi Zhong - Jinan University (China) [presenting]
Abstract: The current Poisson factor models often assume that the factors are unknown, which overlooks the explanatory potential of certain observable covariates. The focus is on high dimensional settings, where the number of the count response variables and/or covariates can diverge as the sample size increases. A covariate-augmented overdispersed Poisson factor model is proposed to jointly perform a high-dimensional Poisson factor analysis and estimate a large coefficient matrix for overdispersed count data. A group of identifiability conditions are provided to guarantee computational identifiability theoretically. The interdependence of both response variables and covariates is incorporated by imposing a low-rank constraint on the large coefficient matrix. A novel variational estimation scheme that combines Laplace and Taylor approximations is proposed to address the computational challenges posed by nonlinearity, two high-dimensional latent matrices, and the low-rank constraint. A criterion based on a singular value ratio is also developed to determine the number of factors and the rank of the coefficient matrix. Comprehensive simulation studies demonstrate that the proposed method outperforms the state-of-the-art methods in estimation accuracy and computational efficiency. An application to the CITE-seq dataset demonstrates the practical merit of the method.
