Publicación:
Finding Near-optimal Configurations in Colossal Spaces with Statistical Guarantees

Vista sencilla de ítem
dc.contributor.authorOh, Jeho
dc.contributor.authorBatory, Don
dc.contributor.authorHeradio Gil, Rubén
dc.date.accessioned2024-06-11T15:15:20Z
dc.date.available2024-06-11T15:15:20Z
dc.date.issued2023-11-23
dc.description.abstractA Software Product Line (SPL) is a family of similar programs. Each program is defined by a unique set of features, called a configuration, that satisfies all feature constraints. “What configuration achieves the best performance for a given workload?” is the SPLOptimization (SPLO) challenge. SPLO is daunting: just 80 unconstrained features yield 1024 unique configurations, which equals the estimated number of stars in the universe. We explain (a) how uniform random sampling and random search algorithms solve SPLO more efficiently and accurately than current machine-learned performance models and (b) how to compute statistical guarantees on the quality of a returned configuration; i.e., it is within x% of optimal with y% confidence.en
dc.description.versionversión final
dc.identifier.doihttps://doi.org/10.1145/3611663
dc.identifier.issn1049-331X; eISSN: 1049-331X
dc.identifier.urihttps://hdl.handle.net/20.500.14468/22384
dc.journal.issue1
dc.journal.titleACM Transactions on Software Engineering and Methodology
dc.journal.volume39
dc.language.isoen
dc.publisherAssociation for Computing Machinery (ACM)
dc.relation.centerE.T.S. de Ingeniería Informática
dc.relation.departmentIngeniería de Software y Sistemas Informáticos
dc.rightsAtribución-NoComercial-SinDerivadas 4.0 Internacional
dc.rightsinfo:eu-repo/semantics/openAccess
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0
dc.subject.keywordssoftware product lines
dc.subject.keywordsconfiguration optimization
dc.subject.keywordsproduct spaces
dc.subject.keywordsmachine learning
dc.subject.keywordsuniform random sampling
dc.subject.keywordsrandom search
dc.subject.keywordsorder statistics
dc.titleFinding Near-optimal Configurations in Colossal Spaces with Statistical Guaranteeses
dc.typeartículoes
dc.typejournal articleen
dspace.entity.typePublication
relation.isAuthorOfPublication38af03ae-439e-45a8-8383-80340d20f7cb
relation.isAuthorOfPublication.latestForDiscovery38af03ae-439e-45a8-8383-80340d20f7cb
Archivos
Bloque original
Mostrando 1 - 1 de 1
Miniatura
Nombre:
Heradio_Ruben_Finding_Near_optimal_Configurat.pdf
Tamaño:
2.3 MB
Formato:
Adobe Portable Document Format
Descargar
Colecciones
Artículos y papers