Surrogate-based methods for black-box optimization

被引：108

作者：

Ky Khac Vu ^{[1
]}

D'Ambrosio, Claudia ^{[1
]}

Hamadi, Youssef ^{[1
]}

Liberti, Leo ^{[1
]}

机构：

[1] Ecole Polytech, CNRS, LIX, Palaiseau, France

来源：

INTERNATIONAL TRANSACTIONS IN OPERATIONAL RESEARCH | 2017年 / 24卷 / 03期

关键词：

simulation optimization; black-box functions; heuristics; optimal control; nonlinear programming; RADIAL BASIS FUNCTIONS; LATIN HYPERCUBE DESIGNS; ADAPTIVE DIRECT SEARCH; GLOBAL OPTIMIZATION; EXPENSIVE FUNCTIONS; COMPUTER EXPERIMENTS; MODEL ALGORITHM; CONSTRUCTION; CONVERGENCE; FRAMEWORK;

D O I：

10.1111/itor.12292

中图分类号：

C93 [管理学];

学科分类号：

12 ; 1201 ; 1202 ; 120202 ;

摘要：

In this paper, we survey methods that are currently used in black-box optimization, that is, the kind of problems whose objective functions are very expensive to evaluate and no analytical or derivative information is available. We concentrate on a particular family of methods, in which surrogate (or meta) models are iteratively constructed and used to search for global solutions.

引用

页码：393 / 424

页数：32

共 66 条

[1]

Abramson M. A., THE NOMAD PROJECT

[2] Multi objective optimization of computationally expensive multi-modal functions with RBF surrogates and multi-rule selection [J].

Akhtar, Taimoor ;

Shoemaker, Christine A. .

JOURNAL OF GLOBAL OPTIMIZATION, 2016, 64 (01) :17-32

[3]

[Anonymous], 2003, QUAL ENG

[4]

[Anonymous], RBFOPT OPEN SOURCE L

[5]

[Anonymous], NEW FRAMEWORK COMBIN

[6]

[Anonymous], 2014, ARXIV14044261

[7]

[Anonymous], PUMAFLOW RESERVOIR S

[8]

[Anonymous], P 14 EUR C MATH OIL

[9]

[Anonymous], 2004, AIAA, DOI /10.2514

[10]

[Anonymous], P 12 EUR C MATH OIL

← 1 2 3 4 5 6 7 →