Title :
Optimization mechanism analysis of evolutionary programming based on a stochastic differential equation model
Author :
Tao, Yongjin ; Shi, Libao ; Ni, Yixin ; Yao, Liangzhong ; Bazargan, Masoud
Author_Institution :
Grad. Sch. at Shenzhen, Tsinghua Univ., Shenzhen, China
Abstract :
As one of evolutionary algorithms, evolutionary programming (EP) has been successfully applied in the solutions of many complex optimization problems. However, little theoretical analysis is carried out to reveal the optimization mechanism of EP. In this paper, a novel stochastic differential equation model is proposed to explore and exploit the dynamic optimization process of EP in theory. The corresponding numerical analysis demonstrates the validity and effectiveness of the proposed model.
Keywords :
differential equations; evolutionary computation; numerical analysis; dynamic optimization process; evolutionary programming; numerical analysis; optimization mechanism analysis; stochastic differential equation model; Analytical models; Convergence; Differential equations; Mathematical model; Numerical models; Optimization; Stochastic processes; evolutionary programming; offline performance; online performance; stochastic differential equation;
Conference_Titel :
Soft Computing and Pattern Recognition (SoCPaR), 2011 International Conference of
Conference_Location :
Dalian
Print_ISBN :
978-1-4577-1195-4
DOI :
10.1109/SoCPaR.2011.6089131
