Total synthesis of algorithmic chemistries
GECCO '05 Proceedings of the 7th annual conference on Genetic and evolutionary computation
Experimental Research in Evolutionary Computation: The New Experimentalism (Natural Computing Series)
Proceedings of the 9th annual conference on Genetic and evolutionary computation
Adaptability of Algorithms for Real-Valued Optimization
EvoWorkshops '09 Proceedings of the EvoWorkshops 2009 on Applications of Evolutionary Computing: EvoCOMNET, EvoENVIRONMENT, EvoFIN, EvoGAMES, EvoHOT, EvoIASP, EvoINTERACTION, EvoMUSART, EvoNUM, EvoSTOC, EvoTRANSLOG
Design and Analysis of Simulation Experiments
Design and Analysis of Simulation Experiments
Comparing parameter tuning methods for evolutionary algorithms
CEC'09 Proceedings of the Eleventh conference on Congress on Evolutionary Computation
Time-bounded sequential parameter optimization
LION'10 Proceedings of the 4th international conference on Learning and intelligent optimization
Experimental Methods for the Analysis of Optimization Algorithms
Experimental Methods for the Analysis of Optimization Algorithms
Hi-index | 0.00 |
Providing tools for algorithm tuning (and the related statistical analysis) is the main topic of this tutorial. This tutorial provides the necessary background for performing algorithm tuning with state-of-the-art tools. We will discuss pros and cons of manual, interactive, and automatic tuning of randomized algorithms such as Genetic Algorithms, Differential Evolution, Particle Swarm, and Evolution Strategies. Moreover, we highlight the important components of experimental work such as proper setup, visualization, and reporting and refer to the most prominent mistakes that may occur, giving examples for failed and successful experiments. The Sequential Parameter Optimization Toolbox (SPOT) is introduced as an example, being freely available via CRAN (free R package server network), see http://cran.r-project.org/web/packages/SPOT/index.html Other tuning approaches such as F-Race, REVAC and ParamILS will be discussed as well.