求解随机混合变分不等式问题的黄金分割算法  

A Golden Ratio Algorithm for Stochastic Mixed Variational Inequalities

作　　者：贺月红 杨澈洲 龙宪军[1] HE Yuehong;YANG Chezhou;LONG Xianjun(College of Mathematics and Statistics,Chongqing Technology and Business University,Chongqing 400067)

机构地区：[1]重庆工商大学数学与统计学院,重庆400067

出　　处：《系统科学与数学》2022年第7期1837-1850,共14页Journal of Systems Science and Mathematical Sciences

基　　金：重庆市自然科学基金(cstc2021jcyj-msxmX0721,cstc2018-jcyjAX0119);重庆市教育委员会科学技术研究重点项目(KJZD-K201900801);重庆市研究生创新型科研项目(CYS22629)资助课题。

摘　　要：引入线性搜索准则,提出了一种新的黄金分割算法求解随机混合变分不等式问题.在不依赖F单调性的条件下,通过构造限制价值函数获得了算法的遍历收敛率和oracle复杂度.数值实验结果显示了算法的有效性.最后给出了算法在随机纳什-古诺博弈问题中的应用.In this paper,we introduce a golden ratio algorithm with line search for solving the stochastic mixed variational inequality problem.Without the assumption of the monotonicity of F,we obtain some results related to the ergodic convergence and the oracle complexity of the proposed algorithm via the restricted merit function.We give some numerical experiments to show the efficiency of the algorithm.Finally,we give an application of the algorithm with respect to the stochastic Nash-Cournot game problem.

关 键 词：随机混合变分不等式 黄金分割算法 线性搜索准则 限制价值函数 

分 类 号：O178[理学—数学]