Large Basic Cone and Sparse Subspace Constrained Nonnegative Matrix Factorization With Kullback-Leibler Divergence for Data Representation

Viet-Hang Duong, Manh-Quan Bui, Yung-Hui Li, Jia-Ching Wang, Tzu-Chiang Tai

Abstract: In this article, a new constrained NMF model with Kullback–Leibler (KL) divergence is developed for data representation. It is called large basic cone and sparse representation-constrained nonnegative matrix factorization with Kullback–Leibler divergence (conespaNMF_KL). It achieves sparseness from a large simplicial cone constraint on the base and sparse regularize on the extracted features.