Optimization Online


Block Coordinate Proximal Gradient Method for Nonconvex Optimization Problems: Convergence Analysis

Xiangfeng Wang (xfwang***at***sei.ecnu.edu.cn)
Xiaoming Yuan (xmyuan***at***hku.hk)
Shangzhi Zeng (zengsz***at***connect.hku.hk)
Jin Zhang (zhangjin198637***at***gmail.com)
Jinchuan Zhou (jinchuanzhou***at***163.com)

Abstract: We propose a block coordinate proximal gradient method for a composite minimization problem with two nonconvex function components in the objective while only one of them is assumed to be differentiable. Under some per-block Lipschitz-like conditions based on Bregman distance, but without the global Lipschitz continuity of the gradient of the differentiable function, we prove that any accumulation point of the sequence is a stationary point of the model. We further show that the stationarity is the ``best" one if the global Lipschitz continuity is additionally assumed, and even the local minimizer for some special cases. Convergence analysis without the global Lipschitz continuity and the enhanced stationarity analysis make our results different from existing results in both the convex and nonconvex contexts.

Keywords: block coordinate proximal gradient method, strong stationarity, convergence analysis

Category 1: Nonlinear Optimization

Category 2: Convex and Nonsmooth Optimization (Nonsmooth Optimization )



Entry Submitted: 04/12/2018
Entry Accepted: 04/12/2018
Entry Last Modified: 08/19/2018

Modify/Update this entry

  Visitors Authors More about us Links
  Subscribe, Unsubscribe
Digest Archive
Search, Browse the Repository


Coordinator's Board
Classification Scheme
Give us feedback
Optimization Journals, Sites, Societies
Mathematical Optimization Society