共轭梯度法和最速下降法的混合算法  

A mixed method of conjugate gradient method and steepest descent method

作　　者：欧志英[1] 严克明[1] 王柏岩[1] 

机构地区：[1]甘肃工业大学基础科学系

出　　处：《甘肃工业大学学报》1999年第1期89-91,共3页Journal of Gansu University of Technology

摘　　要：将共轭梯度法与最速下降法有机地结合起来，构造了一种共轭梯度法和最速下降法的混合算法，并证明了该算法的全局收敛．混合算法既提高了共轭梯度算法的收敛速度，又解决了目标函数“性态不优”时，最速下降法难以求解的问题．同时也可以看到共轭梯度法与最速下降法仅仅是混合算法的特例．The conjugate gradient method and the steepest descent method are combined, and a mixed method of conjugate gradient method and steepest descent is created, and its global convergence is proved. The mixed method raise the convergent rate of the conjugate gradient method, and solve the problem which the steepest descent method can not solve in the condition with badly characteristics for the objective function. In the meantime, it can be seen that the conjugate gradient method or steepest descent method is a special case of the mixed method.

关 键 词：混合算法 共轭梯度法 最速下降法 全局收敛 

分 类 号：O224[理学—运筹学与控制论]