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

• Laura Calvet ^[3] ; Angel A. Juan ^[3] ; Carles Serrat ^[2] ; Jana Ries ^[1]
  1. [1] University of Portsmouth

     University of Portsmouth

     Southsea, Reino Unido

     
  2. [2] Universitat Politècnica de Catalunya

     Universitat Politècnica de Catalunya

     Barcelona, España

     
  3. [3] UOC

  Mostrar afiliaciones +
• Localización: Sort: Statistics and Operations Research Transactions, ISSN 1696-2281, Vol. 40, Nº. 1, 2016, págs. 201-224
• Idioma: inglés
• Enlaces
  • Texto completo
• Dialnet Métricas: 3 Citas
• Resumen

  • Metaheuristics are approximation methods used to solve com binatorial optimization problems.

    Their performance usually depends on a set of parameters tha t need to be adjusted. The selection of appropriate parameter values causes a loss of efficiency, as it requires time, and advanced analytical and problem-specific skills. This paper provide s an overview of the principal approaches to tackle the Parameter Setting Problem, focusing on the sta tistical procedures employed so far by the scientific community. In addition, a novel methodolog y is proposed, which is tested using an already existing algorithm for solving the Multi-Depot V ehicle Routing Problem