A block inertial Bregman proximal algorithm for nonsmooth nonconvex problems with application to symmetric nonnegative matrix tri-factorization
Abstract
We propose BIBPA, a block inertial Bregman proximal algorithm for minimizing the sum of a block relatively smooth function (that is, relatively smooth concerning each block) and block separable nonsmooth nonconvex functions. We prove that the sequence generated by BIBPA subsequentially converges to critical points of the objective under standard assumptions, and globally converges when the objective function is additionally assumed to satisfy the Kurdyka-{\L}ojasiewicz (K{\L}) property. We also provide the convergence rate when the objective satisfies the {\L}ojasiewicz inequality. We apply BIBPA to the symmetric nonnegative matrix tri-factorization (SymTriNMF) problem, where we propose kernel functions for SymTriNMF and provide closed-form solutions for subproblems of BIBPA.
Keywords
Cite
@article{arxiv.2003.03963,
title = {A block inertial Bregman proximal algorithm for nonsmooth nonconvex problems with application to symmetric nonnegative matrix tri-factorization},
author = {Masoud Ahookhosh and Le Thi Khanh Hien and Nicolas Gillis and Panagiotis Patrinos},
journal= {arXiv preprint arXiv:2003.03963},
year = {2020}
}
Comments
18 pages