一类新的锥模型信赖域自适应算法

A new self-adaptive algorithm for trust region of conic model

对于无约束优化问题提出了一类新的结合自适应调节技术和非单调Armijo线搜索技术的锥模型信赖域算法,利用R-函数以变化的速率调节信赖域半径,使信赖域半径调节取决于问题本身,进而减少计算量.在适当的条件下,证明了此算法的全局收敛性.

A new self-adaptive trust algorithm with nonmonotone Armijo line search for unconstrained optimization problems is presented.The trust region radius is updated at a variable rate according to the R-function.This may reduce the number of resolving subproblem as far as possible.Global convergence is proved under certain conditions.