Block Alternating Bregman Majorization Minimization with Extrapolation

Abstract

In this paper, we consider a class of nonsmooth nonconvex optimization problems whose objective is the sum of a block relative smooth function and a proper and lower semicontinuous block separable function. Although the analysis of block proximal gradient (BPG) methods for the class of block $L$-smooth functions have been successfully extended to Bregman BPG methods that deal with the class of block relative smooth functions, accelerated Bregman BPG methods are scarce and challenging to design. Taking our inspiration from Nesterov-type acceleration and the majorization-minimization scheme, we propose a block alternating Bregman Majorization-Minimization framework with Extrapolation (BMME). We prove subsequential convergence of BMME to a first-order stationary point under mild assumptions, and study its global convergence under stronger conditions. We illustrate the effectiveness of BMME on the penalized orthogonal nonnegative matrix factorization problem.

References in corpus (8)

• Fast and Robust Recursive Algorithms for Separable Nonnegative Matrix Factorization
• Inertial Proximal Alternating Linearized Minimization (iPALM) for Nonconvex and Nonsmooth Problems
• Two Algorithms for Orthogonal Nonnegative Matrix Factorization with Application to Clustering
• Hierarchical Clustering of Hyperspectral Images using Rank-Two Nonnegative Matrix Factorization
• Optimization with First-Order Surrogate Functions
• Algorithms for Nonnegative Matrix Factorization with the Kullback-Leibler Divergence
• A Bregman forward-backward linesearch algorithm for nonconvex composite optimization: superlinear convergence to nonisolated local minima
• Beyond Alternating Updates for Matrix Factorization with Inertial Bregman Proximal Gradient Algorithms

Cited by in corpus (1)

• Coordinate projected gradient descent minimization and its application to orthogonal nonnegative matrix factorization