Primal-Dual Algorithms for Non-negative Matrix Factorization with the Kullback-Leibler Divergence

Felipe Yanez (1, 2) , Francis Bach (1, 2)

1 LIENS - Laboratoire d'informatique de l'école normale supérieure
2 SIERRA - Statistical Machine Learning and Parsimony

Non-negative matrix factorization (NMF) approximates a given matrix as a product of two non-negative matrices. Multiplicative algorithms deliver reliable results, but they show slow convergence for high-dimensional data and may be stuck away from local minima. Gradient descent methods have better behavior, but only apply to smooth losses such as the least-squares loss. In this article, we propose a first-order primal-dual algorithm for non-negative decomposition problems (where one factor is fixed) with the KL divergence, based on the Chambolle-Pock algorithm. All required computations may be obtained in closed form and we provide an efficient heuristic way to select step-sizes. By using alternating optimization, our algorithm readily extends to NMF and, on synthetic examples, face recognition or music source separation datasets, it is either faster than existing algorithms, or leads to improved local optima, or both.

Domaines: Apprentissage [cs.LG]; Optimisation et contrôle [math.OC]; Traitement du signal et de l'image [eess.SP]

Felipe Yanez, Francis Bach. Primal-Dual Algorithms for Non-negative Matrix Factorization with the Kullback-Leibler Divergence. 2014. ⟨hal-01079229⟩