Alternative gradient algorithms with applications to nonnegative matrix factorizations

Three nonnegative matrix factorization (NMF) algorithms are discussed and employed to three real-world applications. Based on the alternative gradient algorithm with the iteration steps being determined columnwisely without projection, and columnwisely and elementwisely with projections, three algorithms are developed respectively. Also, the computational costs and the convergence properties of the new algorithms are given. The numerical examples show the advantage of our algorithms over the multiplicative update algorithm proposed by Lee and Seung [11].