Publicación: Finding Near-optimal Configurations in Colossal Spaces with Statistical Guarantees
Cargando...
Fecha
2023-11-23
Autores
Editor/a
Director/a
Tutor/a
Coordinador/a
Prologuista
Revisor/a
Ilustrador/a
Derechos de acceso
Atribución-NoComercial-SinDerivadas 4.0 Internacional
info:eu-repo/semantics/openAccess
info:eu-repo/semantics/openAccess
Título de la revista
ISSN de la revista
Título del volumen
Editor
Association for Computing Machinery (ACM)
Resumen
A 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.
Descripción
Categorías UNESCO
Palabras clave
software product lines, configuration optimization, product spaces, machine learning, uniform random sampling, random search, order statistics
Citación
Centro
E.T.S. de Ingeniería Informática
Departamento
Ingeniería de Software y Sistemas Informáticos