A new algorithm for reducing metaheuristic design effort

Maria Cristina Riff, Elizabeth Montero

Resultado de la investigación: Conference contribution

25 Citas (Scopus)

Resumen

The process of designing a metaheuristic is a difficult and time consuming task as it usually requires tuning to find the best associated parameter values. In this paper, we propose a simple tuning tool called EVOCA which allows unexperimented metaheuristic designers to obtain good quality results without have a strong knowledge in tuning methods. The simplicity here means that the designer does not have to care about the initial settings of the tuner. We apply EVOCA to a genetic algorithm that solves NK landscape instances of various categories. We show that EVOCA is able to tune both categorical and numerical parameters allowing the designer to discard ineffective components for the algorithm.

Idioma originalEnglish
Título de la publicación alojada2013 IEEE Congress on Evolutionary Computation, CEC 2013
Páginas3283-3290
Número de páginas8
DOI
EstadoPublished - 21 ago 2013
Evento2013 IEEE Congress on Evolutionary Computation, CEC 2013 - Cancun, Mexico
Duración: 20 jun 201323 jun 2013

Conference

Conference2013 IEEE Congress on Evolutionary Computation, CEC 2013
PaísMexico
CiudadCancun
Período20/06/1323/06/13

Huella dactilar

Metaheuristics
Tuning
Categorical
Simplicity
Genetic algorithms
Genetic Algorithm
Design

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Theoretical Computer Science

Citar esto

Riff, M. C., & Montero, E. (2013). A new algorithm for reducing metaheuristic design effort. En 2013 IEEE Congress on Evolutionary Computation, CEC 2013 (pp. 3283-3290). [6557972] https://doi.org/10.1109/CEC.2013.6557972
Riff, Maria Cristina ; Montero, Elizabeth. / A new algorithm for reducing metaheuristic design effort. 2013 IEEE Congress on Evolutionary Computation, CEC 2013. 2013. pp. 3283-3290
@inproceedings{854b68f19c3b49c3bba58c3f53cf79c6,
title = "A new algorithm for reducing metaheuristic design effort",
abstract = "The process of designing a metaheuristic is a difficult and time consuming task as it usually requires tuning to find the best associated parameter values. In this paper, we propose a simple tuning tool called EVOCA which allows unexperimented metaheuristic designers to obtain good quality results without have a strong knowledge in tuning methods. The simplicity here means that the designer does not have to care about the initial settings of the tuner. We apply EVOCA to a genetic algorithm that solves NK landscape instances of various categories. We show that EVOCA is able to tune both categorical and numerical parameters allowing the designer to discard ineffective components for the algorithm.",
author = "Riff, {Maria Cristina} and Elizabeth Montero",
year = "2013",
month = "8",
day = "21",
doi = "10.1109/CEC.2013.6557972",
language = "English",
isbn = "9781479904549",
pages = "3283--3290",
booktitle = "2013 IEEE Congress on Evolutionary Computation, CEC 2013",

}

Riff, MC & Montero, E 2013, A new algorithm for reducing metaheuristic design effort. En 2013 IEEE Congress on Evolutionary Computation, CEC 2013., 6557972, pp. 3283-3290, 2013 IEEE Congress on Evolutionary Computation, CEC 2013, Cancun, Mexico, 20/06/13. https://doi.org/10.1109/CEC.2013.6557972

A new algorithm for reducing metaheuristic design effort. / Riff, Maria Cristina; Montero, Elizabeth.

2013 IEEE Congress on Evolutionary Computation, CEC 2013. 2013. p. 3283-3290 6557972.

Resultado de la investigación: Conference contribution

TY - GEN

T1 - A new algorithm for reducing metaheuristic design effort

AU - Riff, Maria Cristina

AU - Montero, Elizabeth

PY - 2013/8/21

Y1 - 2013/8/21

N2 - The process of designing a metaheuristic is a difficult and time consuming task as it usually requires tuning to find the best associated parameter values. In this paper, we propose a simple tuning tool called EVOCA which allows unexperimented metaheuristic designers to obtain good quality results without have a strong knowledge in tuning methods. The simplicity here means that the designer does not have to care about the initial settings of the tuner. We apply EVOCA to a genetic algorithm that solves NK landscape instances of various categories. We show that EVOCA is able to tune both categorical and numerical parameters allowing the designer to discard ineffective components for the algorithm.

AB - The process of designing a metaheuristic is a difficult and time consuming task as it usually requires tuning to find the best associated parameter values. In this paper, we propose a simple tuning tool called EVOCA which allows unexperimented metaheuristic designers to obtain good quality results without have a strong knowledge in tuning methods. The simplicity here means that the designer does not have to care about the initial settings of the tuner. We apply EVOCA to a genetic algorithm that solves NK landscape instances of various categories. We show that EVOCA is able to tune both categorical and numerical parameters allowing the designer to discard ineffective components for the algorithm.

UR - http://www.scopus.com/inward/record.url?scp=84881604119&partnerID=8YFLogxK

U2 - 10.1109/CEC.2013.6557972

DO - 10.1109/CEC.2013.6557972

M3 - Conference contribution

SN - 9781479904549

SP - 3283

EP - 3290

BT - 2013 IEEE Congress on Evolutionary Computation, CEC 2013

ER -

Riff MC, Montero E. A new algorithm for reducing metaheuristic design effort. En 2013 IEEE Congress on Evolutionary Computation, CEC 2013. 2013. p. 3283-3290. 6557972 https://doi.org/10.1109/CEC.2013.6557972