Statistical learning techniques applied to parameter fine-tunig in metaheuristics
Serrat, C.; Calvet , L.; Juan, Á.; Ries, J.
Type of activity
Presentation of work at congresses
Name of edition
CLAPEM 2016 - XIV Latin American Congress of Probability and Mathematical Statistics
Date of publication
Book of congress proceedings
CLAPEM 2016 - XIV Latin American Congress of Probability and Mathematical Statistics [Abstract book]
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 aim of the talk is to focus on
the statistical procedures used so far by the scientific community to tackle the Parameter Setting Problem, and to propose a novel and more efficient methodology. The proposal is tested for the selection of appropriate parameter values for solving the Multi-Depot Vehicle Routing Problem.