NeurIPS 2019
Sun Dec 8th through Sat the 14th, 2019 at Vancouver Convention Center
Paper ID:2399
Title:Beyond Alternating Updates for Matrix Factorization with Inertial Bregman Proximal Gradient Algorithms

The paper introduces a new function generating a Bregman distance and develop Bregman proximal gradient methods applied to various matrix factorization problems. The authors clearly outline the benefits of the approach and computationally demonstrate this.