NEW ALGORITHMS FOR NONNEGATIVE MATRIX COMPLETION

Nonnegative matrix completion aims to find nonnegative low-rank matrices from a subset of entries of a matrix. It is widely applicable in many fields, such as image and video processing, recommendation systems, and national economy. This task can be conducted by solving the nuclear norm regularized linear least squares model with nonnegative constraints. We apply the widely used alternating direction method of multipliers to solve the model and get two novel algorithms. The applicability and efficiency of the new algorithms are demonstrated in numerical experiments. Recovery results show that our algorithms are helpful.