The Interplay of Sampling and Machine Learning for Software Performance Prediction
Christian Kaltenecker, Alexander Grebhahn, Norbert Siegmund, Sven Apel
Abstract
Artificial intelligence has gained considerable momentum in software engineering, but there are major challenges that make this domain special. We review recent advances, raise awareness of the distinctiveness of software configuration spaces, and provide practical guidelines for modeling, predicting, and optimizing performance.
Topics & Concepts
Optimal distinctiveness theoryComputer scienceSoftware engineeringSoftwareDomain (mathematical analysis)Software developmentSocial software engineeringSoftware constructionArtificial intelligenceMachine learningOperating systemPsychologyMathematicsMathematical analysisPsychotherapistSoftware System Performance and ReliabilitySoftware Engineering ResearchSoftware Reliability and Analysis Research