Show simple item record

dc.contributor.author
Waibel, Christoph
dc.contributor.author
Mavromatidis, Georgios
dc.contributor.author
Zhang, Yong-wei
dc.date.accessioned
2020-10-29T17:45:14Z
dc.date.available
2020-10-14T04:18:17Z
dc.date.available
2020-10-29T17:45:14Z
dc.date.issued
2020
dc.identifier.isbn
978-1-7281-6929-3
en_US
dc.identifier.isbn
978-1-7281-6930-9
en_US
dc.identifier.other
10.1109/CEC48606.2020.9185716
en_US
dc.identifier.uri
http://hdl.handle.net/20.500.11850/445843
dc.description.abstract
This paper proposes new Fitness Landscape Analysis (FLA) metrics as measures for problem difficulty in heuristic search. The sensitivity and variable interaction metrics are based on Sobol indices, a common technique in sensitivity analysis. The fitness- and state-variance and the fitness- and state-skewness metrics are based on the second and third central statistical moments. We compute metric values for around 550 continuous test functions in 2, 5 and 10 dimensions and compare it to well-established metrics (Fitness Distance Correlation, Autocorrelation, Information Content, Density-Basin Information and Partial Information Content). By conducting two-sample statistical tests (T-Test, F-Test, Kolmogorov-Smirnov Test, and Rank-Sum Test) for all combinations of FLA metrics, we demonstrate that our proposed metrics result in significantly different distributions. Thus, we can conclude that they reveal fitness landscape characteristics not captured by the existing metrics that were considered.
en_US
dc.language.iso
en
en_US
dc.publisher
IEEE
en_US
dc.subject
Fitness Landscape Analysis
en_US
dc.subject
Sensitivity Analysis
en_US
dc.subject
Central Moments
en_US
dc.subject
Black-Box Optimization
en_US
dc.subject
Problem Difficulty
en_US
dc.title
Fitness Landscape Analysis Metrics based on Sobol Indices and Fitness- And State-Distributions
en_US
dc.type
Conference Paper
dc.date.published
2020-09-03
ethz.book.title
2020 IEEE Congress on Evolutionary Computation (CEC)
en_US
ethz.pages.start
9185716
en_US
ethz.size
8 p.
en_US
ethz.event
IEEE Congress on Evolutionary Computation (CEC 2020) (virtual)
en_US
ethz.event.location
Glasgow, United Kingdom
en_US
ethz.event.date
July 19-24, 2020
en_US
ethz.notes
Due to the Coronavirus (COVID-19) the conference was conducted virtually.
en_US
ethz.identifier.scopus
ethz.publication.place
Piscataway, NJ
en_US
ethz.publication.status
published
en_US
ethz.date.deposited
2020-10-14T04:18:24Z
ethz.source
SCOPUS
ethz.eth
yes
en_US
ethz.availability
Metadata only
en_US
ethz.rosetta.installDate
2020-10-29T17:45:24Z
ethz.rosetta.lastUpdated
2020-10-29T17:45:24Z
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=Fitness%20Landscape%20Analysis%20Metrics%20based%20on%20Sobol%20Indices%20and%20Fitness-%20And%20State-Distributions&rft.date=2020&rft.spage=9185716&rft.au=Waibel,%20Christoph&Mavromatidis,%20Georgios&Zhang,%20Yong-wei&rft.isbn=978-1-7281-6929-3&978-1-7281-6930-9&rft.genre=proceeding&rft_id=info:doi/10.1109/CEC48606.2020.9185716&rft.btitle=2020%20IEEE%20Congress%20on%20Evolutionary%20Computation%20(CEC)
 Search print copy at ETH Library

Files in this item

FilesSizeFormatOpen in viewer

There are no files associated with this item.

Publication type

Show simple item record