In this paper, we propose a new message passing algorithm that utilizes hybrid vector message passing (HVMP) to solve the generalized bilinear factorization (GBF) problem. The proposed GBF-HVMP algorithm integrates expectation propagation (EP) and variational message passing (VMP) via variational free energy minimization, yielding tractable Gaussian messages. Furthermore, GBF-HVMP enables vector/matrix variables rather than scalar ones in message passing, resulting in a loop-free Bayesian network that improves convergence. Numerical results show that GBF-HVMP significantly outperforms state-of-the-art methods in terms of NMSE performance and computational complexity.
Cite
@article{arxiv.2401.03626,
title = {Hybrid Vector Message Passing for Generalized Bilinear Factorization},
author = {Hao Jiang and Xiaojun Yuan and Qinghua Guo},
journal= {arXiv preprint arXiv:2401.03626},
year = {2024}
}