Abstract
In the optimization literature it is frequently assumed that the quality of solutions can be determined by calculating deterministic objective function values. Practical optimization problems, however, often require the evaluation of solutions through experimentation, stochastic simulation, sampling, or even interaction with the user. Thus, most practical problems involve noise. We empirically investigate the robustness of population-based versus point-based optimization methods on a range of parameter optimization problems when noise is added. Our results favor population-based optimization, and the evolution strategy in particular.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
Bäck, T.: Evolutionary Algorithms in Theory and Practice. Oxf. Univ. Press, N.Y. (1996)
Baker, J.E.: Reducing Bias and Inefficiency in the Selection Algorithm. In: Proceedings ICGA II, Lawrence Erlbaum, Hillsdale (1987) 14–21
Beyer, H.-G.: Toward a Theory of ES: Some Asymptotical Results from the (1,+λ)-Theory. Evolutionary Computation 1 (2) (1993) 165–188
Dueck, G.; Scheuer, T.: Threshold Accepting: A General Purpose Optimization Algorithm Appearing Superior to Simulated Annealing. Journal of Comp. Physics 90 (1990) 161–175
Fitzpatrick, J.M.; Grefenstette, J.J.: GA in Noisy Environments. Machine Learning 3 (1988) 101–120
Fogel, D.B.; Ghozeil, A.: Schema Processing Under Proportional Selection in the Presence of Random Effects. IEEE Transactions on Evolutionary Computation 1 (4) (1997) 290–293
Goldberg, D.E.; Deb, K.; Clark, J.H.: Genetic Algorithms, Noise, and the Sizing of Populations. Complex Systems 6 (1992) 333–362
Grefenstette, J.J.; Fitzpatrick, J.M.: Genetic Search with Approximate Function Evalutations. In: Proceedings ICGA I, Lawrence Erlbaum, Hillsdale (1985) 112–120
Grefenstette, J.J.: Deception Considered Harmful. In: Whitley, D. (Ed.): Foundations of Genetic Algorithms 2, Morgan Kaufmann, San Mateo (1993) 75–91
Hammel, U.; Bäck, T.: Evolution Strategies on Noisy Functions. How to Improve Convergence Properties. In: Proceedings PPSN III, Springer, Berlin (1994) 159–168
Miller, B.: Noise, Sampling, and Efficient GAs, Doctoral Thesis, Urbana, Illinois (1997)
Mühlenbein, H.: Evolution in Time and Space. In: Rawlins, G. (ed.): Foundations of Genetic Algorithms, Morgan Kaufmann, San Mateo (1991) 316–337
Nissen, V.; Biethahn, J.: Determining a Good Inventory Policy with a GA. In: Biethahn and Nissen (eds.): Evolutionary Algorithms in Management Applications. Springer, Berlin (1995) 240–249
Nissen, V.; Paul, H.: A Modification of Threshold Accepting and its Application to the Quadratic Assignment Problem. OR Spektrum 17 (1995) 205–210
Nissen, V.; Propach, J.: On the Robustness of Population-Based Versus Point-Based Optimization in the Presence of Noise. To appear in IEEE Transactions on EC
Rana, S.; Whitley, D.; Cogswell, R.: Searching in the Presence of Noise. In: Proceedings PPSN IV, Springer, Berlin (1996) 198–207
Rudolph, G.: Massively Parallel Simulated Annealing and Its Relation to Evolutionary Algorithms. Evolutionary Computation 1 (1993) 361–383
Schwefel, H.-P.: Evolution and Optimum Seeking. Wiley&Sons, New York (1995)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1998 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Nissen, V., Propach, J. (1998). Optimization with noisy function evaluations. In: Eiben, A.E., Bäck, T., Schoenauer, M., Schwefel, HP. (eds) Parallel Problem Solving from Nature — PPSN V. PPSN 1998. Lecture Notes in Computer Science, vol 1498. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0056859
Download citation
DOI: https://doi.org/10.1007/BFb0056859
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-65078-2
Online ISBN: 978-3-540-49672-4
eBook Packages: Springer Book Archive