Title :
On the performance of evolution strategies on noisy PDQFs: Progress rate analysis
Author :
Beyer, Hans-Georg ; Finck, Steffen
Author_Institution :
Vorarlberg Univ. of Appl. Sci., Dornbirn
Abstract :
This paper analyzes the behavior of the (mu/muI,lambda) ES on a class of noisy positive definite quadratic forms (PDQFs). First the equations for the normalized progress rates are derived and then analyzed for constant normalized noise strength and constant (non-normalized) noise strength. Since in the latter case the strategy is not able to reach the optimum, formulas for the final distances to the optimizer (steady state) are derived. The theoretical predictions are then compared with empirical results. In both noise cases the influence of the strategy parameters will be investigated. Further, the equipartition conjecture is used to provide an alternative derivation of the steady state distances in the case of vanishing mutation strength.
Keywords :
evolutionary computation; noise; constant normalized noise strength; equipartition conjecture; evolution strategies; noisy positive definite quadratic forms; progress rate analysis; steady state distances; vanishing mutation strength; Analysis of variance; Electronic switching systems; Equations; Genetic mutations; Information analysis; Noise reduction; Performance analysis; Runtime; Steady-state; Testing;
Conference_Titel :
Evolutionary Computation, 2008. CEC 2008. (IEEE World Congress on Computational Intelligence). IEEE Congress on
Conference_Location :
Hong Kong
Print_ISBN :
978-1-4244-1822-0
Electronic_ISBN :
978-1-4244-1823-7
DOI :
10.1109/CEC.2008.4630843