An experimental study on robust parameter settings

Authors:
Felix Dobslaw
Affiliations:
Mid Sweden University, Östersund, Sweden
Venue:
Proceedings of the 12th annual conference companion on Genetic and evolutionary computation
Year:
2010

Citing 6
Cited 0

Optimization of control parameters for genetic algorithms

IEEE Transactions on Systems, Man and Cybernetics
Efficient Global Optimization of Expensive Black-Box Functions

Journal of Global Optimization
A COMPARATIVE STUDY ON PARTICLE SWARM OPTIMIZATION AND GENETIC ALGORITHMS FOR TRAVELING SALESMAN PROBLEMS

Cybernetics and Systems
ParamILS: an automatic algorithm configuration framework

Journal of Artificial Intelligence Research
No free lunch theorems for optimization

IEEE Transactions on Evolutionary Computation
Parameter control in evolutionary algorithms

IEEE Transactions on Evolutionary Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

That there is no best initial parameter setting for a metaheuristic on all optimization problems is a proven fact (no free lunch theorem). This paper studies the applicability of so called robust parameter settings for combinatorial optimization problems. Design of Experiments supported parameter screening had been carried out, analyzing a discrete Particle Swarm Optimization algorithm on three demographically very dissimilar instances of the Traveling Salesmen Problem. First experimental results indicate that parameter settings produce varying performance quality for the three instances. The robust parameter setting is outperformed in two out of three cases. The results are even significantly worse when considering quality/time trade-off. A methodology for problem generalization is referred to as a possible solution.