OCCVIRMLMay 22, 2019

Beyond Alternating Updates for Matrix Factorization with Inertial Bregman Proximal Gradient Algorithms

arXiv:1905.09050v226 citations
AI Analysis

This addresses a bottleneck in matrix factorization optimization for machine learning and data analysis, offering a more efficient and reliable method.

The paper tackles the bias issue in alternating minimization for matrix factorization by proposing a novel Bregman distance that enables non-alternating schemes with guaranteed convergence, achieving superior performance in speed and objective values in experiments.

Matrix Factorization is a popular non-convex optimization problem, for which alternating minimization schemes are mostly used. They usually suffer from the major drawback that the solution is biased towards one of the optimization variables. A remedy is non-alternating schemes. However, due to a lack of Lipschitz continuity of the gradient in matrix factorization problems, convergence cannot be guaranteed. A recently developed approach relies on the concept of Bregman distances, which generalizes the standard Euclidean distance. We exploit this theory by proposing a novel Bregman distance for matrix factorization problems, which, at the same time, allows for simple/closed form update steps. Therefore, for non-alternating schemes, such as the recently introduced Bregman Proximal Gradient (BPG) method and an inertial variant Convex--Concave Inertial BPG (CoCaIn BPG), convergence of the whole sequence to a stationary point is proved for Matrix Factorization. In several experiments, we observe a superior performance of our non-alternating schemes in terms of speed and objective value at the limit point.

Code Implementations2 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes