loading
Papers

Research.Publish.Connect.

Paper

Paper Unlock

Authors: Christian L. Müeller and Ivo F. Sbalzarini

Affiliation: ETH Zurich, Switzerland

ISBN: 978-989-674-014-6

Keyword(s): Benchmark, Multi-funnel landscape, Lennard-Jones cluster, CMA-ES, Parallel island model.

Related Ontology Subjects/Areas/Topics: Artificial Intelligence ; Computational Intelligence ; Concurrent Co-Operation ; Evolution Strategies ; Evolutionary Computing ; Soft Computing ; Swarm Intelligence

Abstract: A common shortcoming in the Evolutionary Computation (EC) community is that the publication of many search heuristics is not accompanied by rigorous benchmarks on a balanced set of test problems. A welcome effort to promote such test suites are the IEEE CEC competitions on real-valued black-box optimization. These competitions prescribe carefully designed synthetic test functions and benchmarking protocols. They do, however, not contain tunable real-world examples of the important class of multi-funnel functions. We argue that finding minimum-energy configurations of 38-atom Lennard-Jones (LJ38) clusters could serve as such a benchmark for real-valued, single-objective evolutionary optimization. We thus suggest that this problem be included in EC studies whenever general-purpose optimizers are proposed. The problem is tunable from a single-funnel to a double-funnel topology. We show that the winner of the CEC 2005 competition, the Evolution Strategy with Covariance Matrix Adaptation ( CMA-ES), works on the single-funnel version of this test case, but fails on the double-funnel version. We further argue that this performance loss of CMA-ES can be relaxed by using parallel island models. We support this hypothesis by simulation results of a parallel island CMA-ES, the Particle Swarm CMA-ES, on a subset of the multi-funnel functions in the CEC 2005 benchmark. (More)

PDF ImageFull Text

Download
CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 3.91.106.223

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
L. Müeller C.; F. Sbalzarini I. and (2009). A TUNABLE REAL-WORLD MULTI-FUNNEL BENCHMARK PROBLEM FOR EVOLUTIONARY OPTIMIZATION - And Why Parallel Island Models Might Remedy the Failure of CMA-ES on It.In Proceedings of the International Joint Conference on Computational Intelligence - Volume 1: ICEC, (IJCCI 2009) ISBN 978-989-674-014-6, pages 248-253. DOI: 10.5220/0002335202480253

@conference{icec09,
author={Christian {L. Müeller} and Ivo {F. Sbalzarini}},
title={A TUNABLE REAL-WORLD MULTI-FUNNEL BENCHMARK PROBLEM FOR EVOLUTIONARY OPTIMIZATION - And Why Parallel Island Models Might Remedy the Failure of CMA-ES on It},
booktitle={Proceedings of the International Joint Conference on Computational Intelligence - Volume 1: ICEC, (IJCCI 2009)},
year={2009},
pages={248-253},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002335202480253},
isbn={978-989-674-014-6},
}

TY - CONF

JO - Proceedings of the International Joint Conference on Computational Intelligence - Volume 1: ICEC, (IJCCI 2009)
TI - A TUNABLE REAL-WORLD MULTI-FUNNEL BENCHMARK PROBLEM FOR EVOLUTIONARY OPTIMIZATION - And Why Parallel Island Models Might Remedy the Failure of CMA-ES on It
SN - 978-989-674-014-6
AU - L. Müeller, C.
AU - F. Sbalzarini, I.
PY - 2009
SP - 248
EP - 253
DO - 10.5220/0002335202480253

Login or register to post comments.

Comments on this Paper: Be the first to review this paper.