A beginner's guide to tuning methods

Elizabeth Montero, María Cristina Riff, Bertrand Neveu

Research output: Contribution to journalArticlepeer-review

40 Citations (Scopus)

Abstract

Metaheuristic methods have been demonstrated to be efficient tools to solve hard optimization problems. Most metaheuristics define a set of parameters that must be tuned. A good setup of that parameter valuescan lead to take advantage of the metaheuristic capabilities to solve the problem at hand. Tuning strategiesare step by step methods based on multiple runs of the metaheuristic algorithm. In this study we comparefour automated tuning methods: F-Race, Revac, ParamILS and SPO. We evaluate the performance of eachmethod using a standard genetic algorithm for continuous function optimization. We discuss about therequirements of each method, the resources used and quality of solutions found in different scenarios.Finally we establish some guidelines that can help to choose the more appropriate tuning procedure.

Original languageEnglish
Pages (from-to)39-51
Number of pages13
JournalApplied Soft Computing Journal
Volume17
DOIs
Publication statusPublished - 1 Jan 2014

Keywords

  • Evolutionary algorithms
  • Metaheuristics
  • Parameter setting problem
  • Tuning methods

ASJC Scopus subject areas

  • Software

Fingerprint

Dive into the research topics of 'A beginner's guide to tuning methods'. Together they form a unique fingerprint.

Cite this