求解大型最小二乘问题的混合贪婪随机坐标下降法  

HYBRID GREEDY RANDOMIZED COORDINATE DESCENT METHOD FOR SOLVING LARGE-SCALE LINEAR LEAST SQUARE PROBLEM

作　　者：谢亚君 Xie Yajun(School of Big Data&Key Laboratory of Data Science and Intelligent Computing,Fuzhou University of International Studies and Trade,Fuzhou 350202,China)

机构地区：[1]福州外语外贸学院,大数据学院&数据科学与智能计算重点实验室,福州350202

出　　处：《计算数学》2023年第2期230-239,共10页Mathematica Numerica Sinica

基　　金：福建省自然科学基金面上项目(2022J01378);福建省重大教改项目(FBJG20200310)资助。

摘　　要：线性最小二乘问题是科学计算与工程领域普遍存在的问题,有着广泛的应用背景.本文提出了两个新的贪婪随机坐标下降算法来求解大规模的线性最小二乘问题.理论上分析了算法的收敛性.数值实验结果进一步表明了算法的可行性和有效性.Linear least square problem is a universal problem in scientific computing and engineering field which has a wide application background.In this paper,two new greedy random coordinate descent algorithms are proposed to solve large-scale linear least square problem.The convergence of algorithm is analyzed theoretically in details.Numerical tests further verify the feasibility and efficiency of the two algorithms.

关 键 词：线性最小二乘问题 贪婪随机坐标下降法 两步混合加速策略 数值实验 

分 类 号：O224[理学—运筹学与控制论]