Skip to content
Back to outputs

A statistical learning based approach for parameter fine-tuning of metaheuristics

Research output: Contribution to journalArticlepeer-review

Standard

A statistical learning based approach for parameter fine-tuning of metaheuristics. / Calvet, Laura; Juan, Angel A.; Serrat, Carles; Ries, Jana.

In: SORT - Statistics and Operations Research Transactions, Vol. 40, No. 1, 30.06.2016, p. 201-224.

Research output: Contribution to journalArticlepeer-review

Harvard

Calvet, L, Juan, AA, Serrat, C & Ries, J 2016, 'A statistical learning based approach for parameter fine-tuning of metaheuristics', SORT - Statistics and Operations Research Transactions, vol. 40, no. 1, pp. 201-224. <http://www.raco.cat/index.php/SORT/article/view/310078>

APA

Calvet, L., Juan, A. A., Serrat, C., & Ries, J. (2016). A statistical learning based approach for parameter fine-tuning of metaheuristics. SORT - Statistics and Operations Research Transactions, 40(1), 201-224. http://www.raco.cat/index.php/SORT/article/view/310078

Vancouver

Calvet L, Juan AA, Serrat C, Ries J. A statistical learning based approach for parameter fine-tuning of metaheuristics. SORT - Statistics and Operations Research Transactions. 2016 Jun 30;40(1):201-224.

Author

Calvet, Laura ; Juan, Angel A. ; Serrat, Carles ; Ries, Jana. / A statistical learning based approach for parameter fine-tuning of metaheuristics. In: SORT - Statistics and Operations Research Transactions. 2016 ; Vol. 40, No. 1. pp. 201-224.

Bibtex

@article{fd90fb9554074187bebcd766f24fe1bb,
title = "A statistical learning based approach for parameter fine-tuning of metaheuristics",
abstract = "Metaheuristics are approximation methods used to solve combinatorial optimization problems. Their performance usually depends on a set of parameters that need to be adjusted. The selectionof appropriate parameter values causes a loss of efficiency, as it requires time, and advanced analytical and problem-specific skills. This paper provides an overview of the principal approaches to tackle the Parameter Setting Problem, focusing on the statistical procedures employed so far by the scientific community. In addition, a novel methodology is proposed, which is tested using an already existing algorithm for solving the Multi-Depot Vehicle Routing Problem.",
keywords = "Parameter fine-tuning, metaheuristics, statistical learning, biased randomization",
author = "Laura Calvet and Juan, {Angel A.} and Carles Serrat and Jana Ries",
note = "Article does not have a DOI",
year = "2016",
month = jun,
day = "30",
language = "English",
volume = "40",
pages = "201--224",
journal = "SORT - Statistics and Operations Research Transactions",
issn = "1696-2281",
publisher = "Institut d'Estadistica de Catalunya",
number = "1",

}

RIS

TY - JOUR

T1 - A statistical learning based approach for parameter fine-tuning of metaheuristics

AU - Calvet, Laura

AU - Juan, Angel A.

AU - Serrat, Carles

AU - Ries, Jana

N1 - Article does not have a DOI

PY - 2016/6/30

Y1 - 2016/6/30

N2 - Metaheuristics are approximation methods used to solve combinatorial optimization problems. Their performance usually depends on a set of parameters that need to be adjusted. The selectionof appropriate parameter values causes a loss of efficiency, as it requires time, and advanced analytical and problem-specific skills. This paper provides an overview of the principal approaches to tackle the Parameter Setting Problem, focusing on the statistical procedures employed so far by the scientific community. In addition, a novel methodology is proposed, which is tested using an already existing algorithm for solving the Multi-Depot Vehicle Routing Problem.

AB - Metaheuristics are approximation methods used to solve combinatorial optimization problems. Their performance usually depends on a set of parameters that need to be adjusted. The selectionof appropriate parameter values causes a loss of efficiency, as it requires time, and advanced analytical and problem-specific skills. This paper provides an overview of the principal approaches to tackle the Parameter Setting Problem, focusing on the statistical procedures employed so far by the scientific community. In addition, a novel methodology is proposed, which is tested using an already existing algorithm for solving the Multi-Depot Vehicle Routing Problem.

KW - Parameter fine-tuning

KW - metaheuristics

KW - statistical learning

KW - biased randomization

UR - http://www.raco.cat/index.php/SORT/issue/view/23676/showToc

M3 - Article

VL - 40

SP - 201

EP - 224

JO - SORT - Statistics and Operations Research Transactions

JF - SORT - Statistics and Operations Research Transactions

SN - 1696-2281

IS - 1

ER -

ID: 4289301