PROJECT TITLE :

Fast Low-Rank Bayesian Matrix Completion With Hierarchical Gaussian Prior Models - 2018

ABSTRACT:

The problem of low-rank matrix completion is taken into account in this Project. To use the underlying low-rank structure of the data matrix, we tend to propose a hierarchical Gaussian previous model, where columns of the low-rank matrix are assumed to follow a Gaussian distribution with zero mean and a standard precision matrix, and a Wishart distribution is specified as a hyperprior over the precision matrix. We tend to show that such a hierarchical Gaussian previous has the potential to encourage a coffee-rank solution. Based on the proposed hierarchical previous model, we have a tendency to develop a variational Bayesian matrix completion method, which embeds the generalized approximate massage passing technique to bypass cumbersome matrix inverse operations. Simulation results show that our proposed methodology demonstrates superiority over some state-of-the-art matrix completion strategies.