Title :
On the analysis of self-adaptive recombination strategies: first results
Author :
Meyer-Nieberg, Silja ; Beyer, Hans-Georg
Author_Institution :
Dept. of Comput. Sci., Dortmund Univ., Germany
Abstract :
This paper presents first results on the analysis of self-adaptive (μ/μI, λ)-evolution strategies (ES). Applying a deterministic approach to model the evolution of the ES, equations describing the stationary state behavior of the normalized mutation strength and of the progress rate is derived. The analysis provides a deeper insight as to why the performance of the ES exhibits a sensitive dependence on the learning parameter τ.
Keywords :
evolutionary computation; function approximation; learning (artificial intelligence); probability; deterministic approach; evolution strategies; mutation strength; self-adaptive recombination; stationary state behavior; Computer science; Equations; Genetic mutations; Optimization methods; Performance analysis; Probability density function; Random variables; Scalability; Size control; Stationary state;
Conference_Titel :
Evolutionary Computation, 2005. The 2005 IEEE Congress on
Print_ISBN :
0-7803-9363-5
DOI :
10.1109/CEC.2005.1554986
