Please use this identifier to cite or link to this item:
Full metadata record
DC FieldValueLanguage
dc.contributor.authorThomson, Sarahen_UK
dc.contributor.authorOchoa, Gabrielaen_UK
dc.description.abstractWe propose looking at the phenomenon of fitness landscape funnels in terms of their depth. In particular, we examine how the depth of funnels in Local Optima Networks (LONs) of benchmark Quadratic Assignment Problem instances relate to metaheuristic performance. Three distinct iterated local search (ILS) acceptance strategies are considered: better-or-equal (standard), annealing-like, and restart. Funnel measurements are analysed for their connection to ILS performance on the underlying combinatorial problems. We communicate the findings through hierarchical clustering of LONs, network visualisations, subgroup analysis, correlation analysis, and Random Forest regression models. The results show that funnel depth is associated with search difficulty, and that there is an interplay between funnel structure and acceptance strategy. Standard and annealing acceptance work better than restart on both deep-funnel and shallow-funnel problems; standard acceptance is the best strategy when optimal funnel(s) are deep, while annealing acceptance is superior when they are shallow. Regression models including funnel depth measurements could explain up to 96% of ILS runtime variance (with annealing-like acceptance). The runtime of ILS with restarts was less explainable using funnel features.en_UK
dc.relationThomson S & Ochoa G (2022) On Funnel Depths and Acceptance Criteria in Stochastic Local Search. In: GECCO '22: Proceedings of the Genetic and Evolutionary Computation Conference. Genetic and Evolutionary Computation Conference (GECCO) 2022, Boston, USA, 09.07.2022-13.07.2022. New York: ACM, pp. 287-295.;
dc.rightsThis item has been embargoed for a period. During the embargo please use the Request a Copy feature at the foot of the Repository record to request a copy directly from the author. You can only request a copy if you wish to use this work for your own research or private study. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in GECCO ’22, July 9–13, 2022, Boston, MA, USA
dc.titleOn Funnel Depths and Acceptance Criteria in Stochastic Local Searchen_UK
dc.typeConference Paperen_UK
dc.rights.embargoreason[gecco 2022 paper.pdf] Until this work is published there will be an embargo on the full text of this work.en_UK
dc.type.statusAM - Accepted Manuscripten_UK
dc.citation.btitleGECCO '22: Proceedings of the Genetic and Evolutionary Computation Conferenceen_UK
dc.citation.conferencedates2022-07-09 - 2022-07-13en_UK
dc.citation.conferencelocationBoston, USAen_UK
dc.citation.conferencenameGenetic and Evolutionary Computation Conference (GECCO) 2022en_UK
dc.publisher.addressNew Yorken_UK
dc.contributor.affiliationComputing Scienceen_UK
dc.contributor.affiliationComputing Scienceen_UK
rioxxterms.apcnot requireden_UK
rioxxterms.typeConference Paper/Proceeding/Abstracten_UK
local.rioxx.authorThomson, Sarah|0000-0001-6971-7817en_UK
local.rioxx.authorOchoa, Gabriela|0000-0001-7649-5669en_UK
local.rioxx.projectInternal Project|University of Stirling|
local.rioxx.filenamegecco 2022 paper.pdfen_UK
Appears in Collections:Computing Science and Mathematics Conference Papers and Proceedings

Files in This Item:
File Description SizeFormat 
gecco 2022 paper.pdfFulltext - Accepted Version1.63 MBAdobe PDFView/Open

This item is protected by original copyright

Items in the Repository are protected by copyright, with all rights reserved, unless otherwise indicated.

The metadata of the records in the Repository are available under the CC0 public domain dedication: No Rights Reserved

If you believe that any material held in STORRE infringes copyright, please contact providing details and we will remove the Work from public display in STORRE and investigate your claim.