摘要
基于新拟牛顿方程,提出一类保守修正BFGS算法.该算法的特点是:即使当目标函数是非凸函数时,该算法仍然是全局收敛的.在适当的条件下,该算法具有局部超线性收敛性.初步的数值实验表明,该算法是有效的.
A cautious BFGS-type algorithm based on a new secant equation was this version of BFGS algorithm was that this algorithm possessed global convergence even when the objective function was nonconvex. In the proper conditions, the cautious BFGS-type algorithm was superlinearly convergent. The numerical experiments showed that the cautious BFGS-type algorithm was promising.
出处
《集美大学学报（自然科学版）》
CAS
2010年第3期228-233,共6页
Journal of Jimei University：Natural Science
基金
国家自然科学基金资助项目(10471036)
集美大学科研基金资助项目(C60657)
