Theory of evolution strategies - a tutorial
Theoretical aspects of evolutionary computing
Evolution strategies –A comprehensive introduction
Natural Computing: an international journal
Step-Size Adaption Based on Non-Local Use of Selection Information
PPSN III Proceedings of the International Conference on Evolutionary Computation. The Third Conference on Parallel Problem Solving from Nature: Parallel Problem Solving from Nature
Introduction to Stochastic Search and Optimization
Introduction to Stochastic Search and Optimization
A New Approach for Predicting the Final Outcome of Evolution Strategy Optimization Under Noise
Genetic Programming and Evolvable Machines
Completely Derandomized Self-Adaptation in Evolution Strategies
Evolutionary Computation
Step length adaptation on ridge functions
Evolutionary Computation
Proceedings of the 11th Annual conference on Genetic and evolutionary computation
The steady state behavior of (µ/µI, λ)-ES on ellipsoidal fitness models disturbed by noise
GECCO'03 Proceedings of the 2003 international conference on Genetic and evolutionary computation: PartI
Performance of the (µ/µ, λ)-σSA-ES on a class of PDQFs
IEEE Transactions on Evolutionary Computation
Optimal weighted recombination
FOGA'05 Proceedings of the 8th international conference on Foundations of Genetic Algorithms
Noisy optimization: a theoretical strategy comparison of ES, EGS, SPSA & IF on the noisy sphere
Proceedings of the 13th annual conference on Genetic and evolutionary computation
Natural evolution strategies converge on sphere functions
Proceedings of the 14th annual conference on Genetic and evolutionary computation
Hi-index | 5.23 |
To theoretically compare the behavior of different algorithms, compatible performance measures are necessary. Thus in the first part, an analysis approach, developed for evolution strategies, was applied to simultaneous perturbation stochastic approximation on the noisy sphere model. A considerable advantage of this approach is that convergence results for non-noisy and noisy optimization can be obtained simultaneously. Next to the convergence rates, optimal step sizes and convergence criteria for 3 different noise models were derived. These results were validated by simulation experiments. Afterward, the results were used for a comparison with evolution strategies on the sphere model in combination with the 3 noise models. It was shown that both strategies perform similarly, with a slight advantage for SPSA if optimal settings are used and the noise strength is not too large.