Evolutionary Algorithms in the Presence of Noise: To Sample or Not to Sample

In this paper, we empirically analyze the convergence behavior of evolutionary algorithms (evolution strategies - ES and genetic algorithms A) for two noisy optimization problems which belong to the class of functions with noise induced multi-modality (FNIMs). Although, both functions are qualitatively very similar, the ES is only able to converge to the global optimizer state for one of them. Additionally, we observe that canonical GA exhibits similar problems. We present a theoretical analysis which explains the different behaviors for the two functions and which suggests to resort to resampling strategies to solve the problem. Although, resampling is an inefficient way to cope with noisy optimization problems, it turns out that depending on the properties of the problem, (moderate) resampling might be necessary to guarantee convergence to the robust optimizer

[1]  Shigeyoshi Tsutsui,et al.  A comparative study on the effects of adding perturbations to phenotypic parameters in genetic algorithms with a robust solution searching scheme , 1999, IEEE SMC'99 Conference Proceedings. 1999 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No.99CH37028).

[2]  Bernhard Sendhoff,et al.  On the Behavior of (μ/μ1, λ)-ES Optimizing Functions Disturbed by Generalized Noise , 2002, FOGA.

[3]  Bernhard Sendhoff,et al.  Functions with noise-induced multimodality: a test for evolutionary robust Optimization-properties and performance analysis , 2006, IEEE Transactions on Evolutionary Computation.

[4]  Bernhard Sendhoff,et al.  Advanced High Turning Compressor Airfoils for Low Reynolds Number Condition: Part 1 — Design and Optimization , 2003 .

[5]  Nikolaus Hansen,et al.  On the Adaptation of Arbitrary Normal Mutation Distributions in Evolution Strategies: The Generating Set Adaptation , 1995, ICGA.

[6]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[7]  Hans-Georg Beyer,et al.  Actuator Noise in Recombinant Evolution Strategies on General Quadratic Fitness Models , 2004, GECCO.

[8]  Goldberg,et al.  Genetic algorithms , 1993, Robust Control Systems with Genetic Algorithms.

[9]  J. Fitzpatrick,et al.  Genetic Algorithms in Noisy Environments , 2005, Machine Learning.

[10]  Shigeyoshi Tsutsui,et al.  Genetic algorithms with a robust solution searching scheme , 1997, IEEE Trans. Evol. Comput..

[11]  Kalyanmoy Deb,et al.  Simulated Binary Crossover for Continuous Search Space , 1995, Complex Syst..

[12]  Heinz Mühlenbein,et al.  Fuzzy Recombination for the Breeder Genetic Algorithm , 1995, ICGA.

[13]  Nikolaus Hansen,et al.  Adapting arbitrary normal mutation distributions in evolution strategies: the covariance matrix adaptation , 1996, Proceedings of IEEE International Conference on Evolutionary Computation.

[14]  Markus Olhofer,et al.  Advanced high turning compressor airfoils for low Reynolds number condition. Part I: Design and optimization , 2004 .

[15]  Hans-Georg Beyer,et al.  Qualms Regarding the Optimality of Cumulative Path Length Control in CSA/CMA-Evolution Strategies , 2003, Evolutionary Computation.

[16]  Bernhard Sendhoff,et al.  The Influence of stochastic Quality Functions on Evolutionary Search , 2002, SEAL.

[17]  Bernhard Sendhoff,et al.  Evolution Strategies for Robust Optimization , 2006, 2006 IEEE International Conference on Evolutionary Computation.