Robust Gaussian FunctionAlgorithm forMatrix Completion

Abstract

This paper introduces a novel algorithm to solve the matrix rank minimization problem among all matrices obeying a set of convex constraints. The most popular convex relaxation of the rank minimization problem minimizes the nuclear norm instead of the rank of the matrix. In this paper we are interested in using robust Gaussian function to solve the low-rank matrix completion problem, which is the special case of the rank minimization problem. This regularized problem is a differential smooth convex optimization problem, in which the