Algorithm selection based on exploratory landscape analysis and cost-sensitive learning

Authors:
Bernd Bischl;Olaf Mersmann;Heike Trautmann;Mike Preuß
Affiliations:
TU Dortmund, Dortmund, Germany;TU Dortmund, Dortmund, Germany;TU Dortmund, Dortmund, Germany;TU Dortmund, Dortmund, Germany
Venue:
Proceedings of the 14th annual conference on Genetic and evolutionary computation
Year:
2012

Citing 6
Cited 3

Fitness Distance Correlation as a Measure of Problem Difficulty for Genetic Algorithms

Proceedings of the 6th International Conference on Genetic Algorithms
PISA: a platform and programming language independent interface for search algorithms

EMO'03 Proceedings of the 2nd international conference on Evolutionary multi-criterion optimization
Black-box optimization benchmarking of NEWUOA compared to BIPOP-CMA-ES: on the BBOB noiseless testbed

Proceedings of the 12th annual conference companion on Genetic and evolutionary computation
Comparing results of 31 algorithms from the black-box optimization benchmarking BBOB-2009

Proceedings of the 12th annual conference companion on Genetic and evolutionary computation
Benchmarking evolutionary algorithms: towards exploratory landscape analysis

PPSN'10 Proceedings of the 11th international conference on Parallel problem solving from nature: Part I
Exploratory landscape analysis

Proceedings of the 13th annual conference on Genetic and evolutionary computation

A feature-based comparison of local search and the christofides algorithm for the travelling salesperson problem

Proceedings of the twelfth workshop on Foundations of genetic algorithms XII
Recent advances in problem understanding: changes in the landscape a year on

Proceedings of the 15th annual conference companion on Genetic and evolutionary computation
A novel feature-based approach to characterize algorithm performance for the traveling salesperson problem

Annals of Mathematics and Artificial Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

The steady supply of new optimization methods makes the algorithm selection problem (ASP) an increasingly pressing and challenging task, specially for real-world black-box optimization problems. The introduced approach considers the ASP as a cost-sensitive classification task which is based on Exploratory Landscape Analysis. Low-level features gathered by systematic sampling of the function on the feasible set are used to predict a well-performing algorithm out of a given portfolio. Example-specific label costs are defined by the expected runtime of each candidate algorithm. We use one-sided support vector regression to solve this learning problem. The approach is illustrated by means of the optimization problems and algorithms of the BBOB'09/10 workshop.