非凸两分块优化问题的一类惯性对称正则化交替方向乘子法  

A class of inertial symmetric regularization alternating direction method of multipliers for nonconvex two-block optimization*

作　　者：彭建文 雷宏旺 PENG Jianwen;LEI Hongwang(College of Mathematical Sciences,Chongqing Normal University,Chongqing 401331,China)

机构地区：[1]重庆师范大学数学科学学院,重庆401331

出　　处：《运筹学学报》2023年第3期37-52,共16页Operations Research Transactions

基　　金：国家自然科学基金重大项目(No.11991024);国家自然科学基金面上项目(12271071);重庆英才·创新创业领军人才·创新创业示范团队项目(No.CQYC20210309536);重庆市高校创新研究群体项目(No.CXQT20014);重庆市自然科学基金(No.cstc2021jcyj-msxmX0300)。

摘　　要：交替方向乘子法(ADMM)是一个求解可分离凸优化问题的的有效方法,然而,当目标函数存在非凸函数时,ADMM或许不收敛。本文提出一类带线性等式约束的非凸两分块优化问题的惯性对称正则化交替方向乘子法。在适当的假设条件下,建立了算法的全局收敛性。其次,在效益函数满足Kurdyka-?ojasiewicz(KL)性质时,建立了算法的强收敛性。最后,对算法进行了数值实验,结果说明算法是一种有效的方法。The alternating direction method of multipliers(ADMM)is an valid method for solving separable convex optimization problems,nevertheless,when the objective function has a nonconvex function,ADMM may not converge.This paper proposes an inertial symmetric regularization alternating direction method of multipliers for nonconvex two-block optimization problem with linear equality constraints.Under the appropriate hypothesis conditions,the global convergence of the algorithm is established.Secondly,When the benefit function satisfies the Kurdyka-Lojasiewicz(KL)property,the strong convergence of the algorithm is established.Finally,numerical experiments are performed on the algorithm,and the results show that the algorithm is an effective method.

关 键 词：交替方向乘子法 非凸优化问题 Kurdyka-Lojasiewicz(KL)性质 收敛性 

分 类 号：O221.6[理学—运筹学与控制论]