A New Supermemory Gradient Method without Line Search for Unconstrained Optimization

被引：0

作者：

Liu, June ^{[1
]}

Liu, Huanbin ^{[1
]}

Zheng, Yue ^{[1
]}

机构：

[1] Huanggang Normal Univ, Inst Uncertain Syst, Coll Math & Informat Sci, Huanggang 438000, Hubei, Peoples R China

来源：

SIXTH INTERNATIONAL SYMPOSIUM ON NEURAL NETWORKS (ISNN 2009) | 2009年 / 56卷

关键词：

Unconstrained optimization; Memory gradient method; Global convergence; Convergence rate; GLOBAL CONVERGENCE; DESCENT METHODS; FAMILY;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper, we present a new supermemory gradient method without line search for unconstrained optimization problems. The new method can guarantee a descent at each iteration. It sufficiently uses the previous multi-step iterative information at each iteration and avoids the storage and computation of matrices associated with the Hessian of objective functions, so that it is suitable to solve large scale optimization problems. We also prove its global convergence under some mild conditions. In addition, We analyze the linear convergence rate of the new method when the objective function is uniformly convex and twice continuously differentiable.

引用

页码：641 / 647

页数：7

共 18 条

[11] Global convergence of shortest-residual family of conjugate gradient methods without line search [J].