An estimation distribution algorithm with the spearman's rank correlation index

This article arguments that rank correlation coefficients are powerful association measures and how can they be adopted by EDAs. A new EDA implements the proposed ideas: the Non-Parametric Real-valued Estimation Distribution Algorithm (NOPREDA). The paper fully describes the rank correlation coefficient, and the procedure to build a non parametric model for the probability distribution of the source data. A benchmark of global optimization problems is solved with NOPREDA. Categories and Subject Descriptors: J.2[Physical Sciences and Engineering]Mathematics and Statistics General Terms: Algorithms, Design, Performance.

• Type: Conference
• Year: 2008
• Where: GECCO
• Authors: Arturo Hernández Aguirre, Enrique Raúl Villa Diharce, Selma Barba-Moreno
• Keywords: GECCO 2008, Non-Parametric Real-valued Estimation, Optimization, Powerful Association Measures, Rank Correlation Coefficient