Design of evolutionary algorithms-A statistical perspective Export

@article{citeulike:344087, abstract = {This paper describes a statistical method that helps to find good parameter settings for evolutionary algorithms. The method builds a functional relationship between the algorithm's performance and its parameter values. This relationship-a statistical model-can be identified thanks to simulation data. Estimation and test procedures are used to evaluate the effect of parameter variation. In addition, good parameter settings can be investigated with a reduced number of experiments. Problem labeling can also be considered as a model variable and the method enables identifying classes of problems for which the algorithm behaves similarly. Defining such classes increases the quality of estimations without increasing the computational cost}, author = {Francois, O. and Lavergne, C.}, citeulike-article-id = {344087}, citeulike-linkout-0 = {http://dx.doi.org/10.1109/4235.918434}, citeulike-linkout-1 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=918434}, day = {07}, doi = {10.1109/4235.918434}, journal = {Evolutionary Computation, IEEE Transactions on}, keywords = {ea}, month = {August}, number = {2}, pages = {129--148}, posted-at = {2009-10-04 12:12:13}, priority = {2}, title = {Design of evolutionary algorithms-A statistical perspective}, url = {http://dx.doi.org/10.1109/4235.918434}, volume = {5}, year = {2002} }

TY - JOUR ID - citeulike:344087 L3 - citeulike-article-id:344087 N2 - This paper describes a statistical method that helps to find good parameter settings for evolutionary algorithms. The method builds a functional relationship between the algorithm's performance and its parameter values. This relationship-a statistical model-can be identified thanks to simulation data. Estimation and test procedures are used to evaluate the effect of parameter variation. In addition, good parameter settings can be investigated with a reduced number of experiments. Problem labeling can also be considered as a model variable and the method enables identifying classes of problems for which the algorithm behaves similarly. Defining such classes increases the quality of estimations without increasing the computational cost IS - 2 JF - Evolutionary Computation, IEEE Transactions on EP - 148 TI - Design of evolutionary algorithms-A statistical perspective VL - 5 SP - 129 KW - ea AU - Francois, O AU - Lavergne, C PY - 2002/08/07/ UR - http://dx.doi.org/10.1109/4235.918434 ER -