新的非单调线搜索规则BFGS算法的全局收敛性

Global Convergence Results of BFGS Methods with New Nonmonotone Step Size Rule

本文在Zhang H.C.的非单调线搜索规则的基础上,设计了求解无约束最优化问题的新的非单调线搜索BFGS算法,在一定的条件下证明了算法的线性收敛性和超线性收敛性分析.数值例子表明算法是有效的.

We propose a new nonmonotone step size rule and analyze the global convergence of new BFGS quasi-Newton method.The new step size rule is similar to Zhang H.C.nonmonotone step size rule and contains it as a special case.Numerical experiments have been conducted which show that the proposed algorithm is encouraging.