The directional EDA for global optimization

This article presents a robust EDA for global optimization with real parameters. The approach is based on the linear combination of individuals of two populations. One is the current population Pt, from which a probability density model is created and a new population Ps is simulated. The new population Pt+1 is a linear combination of Pt and Ps. The linear combination factor involved is self-adaptive. 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: Pedro P. Mayorga-Alvarez, Arturo Hernández Aguirre
• Keywords: Current Population Pt, GECCO 2008, Linear Combination, Linear Combination Factor, Optimization