Large Scale Parameter Meta-Optimization of Metaheuristic Optimization Algorithms with HeuristicLab Hive

Created by W.Langdon from gp-bibliography.bib Revision:1.8051

@InProceedings{2743,

• author = "Christoph Neumueller and Andreas Scheibenpflug and Stefan Wagner and Andreas Beham and Michael Affenzeller",
• title = "Large Scale Parameter Meta-Optimization of Metaheuristic Optimization Algorithms with HeuristicLab Hive",
• booktitle = "Proceedings of the 8th spanish congress on Metaheuristics, Evolutionary and Bioinspired Algorithms (MAEB'2012)",
• year = "2012",
• editor = "Jose Antonio Gamez Martin and Jose Miguel Puerta Callejon",
• address = "Albacete, Spain",
• month = "8-10 " # feb,
• organisation = "Grupo de Sistemas Inteligentes y Mineria de Datos, perteneciente a la Universidad de Castilla-La Mancha (UCLM), Spain",
• keywords = "genetic algorithms, genetic programming, PMO",
• URL = "http://research.fh-ooe.at/files/publications/2743_MAEB2012.pdf",
• URL = "https://www.researchgate.net/profile/Andreas_Beham/publication/230701425_Large_Scale_Parameter_Meta-Optimization_of_Metaheuristic_Optimization_Algorithms_with_HeuristicLab_Hive/links/00b7d5332f7035c977000000/Large-Scale-Parameter-Meta-Optimization-of-Metaheuristic-Optimization-Algorithms-with-HeuristicLab-Hive.pdf",
• code_url = "http://dev.heuristiclab.com",
• size = "8 pages",
• abstract = "many different metaheuristic algorithms have been developed and applied to various problems. According to the no free lunch theorem no single algorithm exists that can solve all problems better than all other algorithms. This is one of the reasons why metaheuristic algorithms often have parameters which allow them to change their behaviour in a certain range. However, finding good parameter values is not trivial and requires human expertise as well as time. The search for optimal parameter values can be seen as an optimisation problem itself which can be solved by a metaheuristic optimization algorithm (meta-optimisation). metaoptimization implementation for the heuristic optimisation environment HeuristicLab. Because meta-optimization is extremely run time intensive, a distributed computation infrastructure, HeuristicLabHive, is used and will be described. To demonstrate the effectiveness of the implementation, a number of parameter optimisation experiments are performed and analysed.",
• notes = "MAEB-2012 broken 2021 http://simd.albacete.org/maeb2012/index.php/sepconferencia",

}

Genetic Programming entries for Christoph Neumueller Andreas Scheibenpflug Stefan Wagner Andreas Beham Michael Affenzeller

Citations