Lower Bounds on the Convergence Rate of the Markov Symmetric Random Search

被引:2
|
作者
Tikhomirov, A. S. [1 ]
机构
[1] Novgorod State Univ, Velikiy Novgorod 173003, Russia
关键词
random search; global optimization; stochastic optimization; estimate of convergence rate;
D O I
10.1134/S0965542511090168
中图分类号
O29 [应用数学];
学科分类号
070104 ;
摘要
The convergence rate of the Markov random search algorithms designed for finding the extremizer of a function is investigated. It is shown that, for a wide class of random search methods that possess a natural symmetry property, the number of evaluations of the objective function needed to find the extremizer accurate to cannot grow slower than vertical bar ln epsilon vertical bar.
引用
收藏
页码:1524 / 1538
页数:15
相关论文
共 50 条