An Inertial Block Majorization Minimization Framework for Nonsmooth Nonconvex Optimization

arXiv2010.12133MaRDI QIDQ6352041

Author name not available (Why is that?)

Publication date: 22 October 2020

Abstract: In this paper, we introduce TITAN, a novel inerTIal block majorizaTion minimizAtioN framework for non-smooth non-convex optimization problems. To the best of our knowledge, TITAN is the first framework of block-coordinate update method that relies on the majorization-minimization framework while embedding inertial force to each step of the block updates. The inertial force is obtained via an extrapolation operator that subsumes heavy-ball and Nesterov-type accelerations for block proximal gradient methods as special cases. By choosing various surrogate functions, such as proximal, Lipschitz gradient, Bregman, quadratic, and composite surrogate functions, and by varying the extrapolation operator, TITAN produces a rich set of inertial block-coordinate update methods. We study sub-sequential convergence as well as global convergence for the generated sequence of TITAN. We illustrate the effectiveness of TITAN on two important machine learning problems, namely sparse non-negative matrix factorization and matrix completion.

Has companion code repository: https://github.com/nhatpd/TITAN

This page was built for publication: An Inertial Block Majorization Minimization Framework for Nonsmooth Nonconvex Optimization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6352041)