Separable Nonnegative Matrix Factorization Using Powered Ratio-of-Norms Regularization
This work develops efficient algorithms based on the difference-of-convex function algorithm (DCA) and the alternating direction method of multipliers (ADMM) to enhance sparsity and identifiability of the learned factors in separable nonnegative matrix factorization.
Matthew McCarver, Jing Qin
· 0 citations