基于简单二次函数模型的非单调自适应信赖域算法  

A Nonmontone Self-adaptive Trust Region Algorithm Based on a Simple Quadratic Model

作　　者：冯琳[1] 段复建[1] 

机构地区：[1]桂林电子科技大学数学与计算科学学院,广西桂林541004

出　　处：《信阳师范学院学报（自然科学版）》2011年第1期38-42,共5页Journal of Xinyang Normal University(Natural Science Edition)

摘　　要：基于简单二次函数模型,结合非单调技术和自适应技术,建立了一个求解无约束最优化问题的非单调自适应信赖域算法,并在适当的条件下,证明了算法的全局收敛性和超线性收敛性.理论分析算法是有效的,适合求解大规模问题.Based on the simple quadratic model, nonmonotone technique and adaptive technique are combined to propose a nonmonotone self-adaptive trust region algorithm for unconstrained optimization problems. The global and superlinear convergence results of the nonmonotone self-adaptive trust region method are proved under mild conditions. Theoretical analysis shows that the algorithm is efficient and attractive for large-scaled optimization problems.

关 键 词：非单调 自适应 信赖域算法 全局收敛性 超线性收敛性 

分 类 号：O221.2[理学—运筹学与控制论]