SNOBFIT - Stable noisy optimization by branch and fit
SNOBFIT - Stable noisy optimization by branch and fit
复制标题
DOI：
10.1145/1377612.1377613
复制
发表时间：
2008-07-01
影响因子：
2.7
通讯作者：
Neumaier, Arnold
中科院分区：
文献类型：
--
作者：
Huyer, Waltraud;Neumaier, Arnold
软件包SNOBFIT的有界约束（和软约束）噪声优化的昂贵的目标函数。它通过分支和局部拟合将全局和局部搜索结合起来。通过允许隐藏约束、批函数求值、搜索区域的改变等，该程序对于实际使用是鲁棒的和灵活的。
The software package SNOBFIT for bound-constrained (and soft-constrained) noisy optimization of an expensive objective function is described. It combines global and local search by branching and local fits. The program is made robust and flexible for practical use by allowing for hidden constraints, batch function evaluations, change of search regions, etc.