Towards Feature-Based Performance Regression Using Trajectory Data
| العنوان: | Towards Feature-Based Performance Regression Using Trajectory Data |
|---|---|
| المؤلفون: | Anja Jankovic, Tome Eftimov, Carola Doerr |
| المساهمون: | Recherche Opérationnelle (RO), LIP6, Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS), Centre National de la Recherche Scientifique (CNRS), Sorbonne Université (SU) |
| المصدر: | Applications of Evolutionary Computation 24th International Conference, EvoApplications 2021, Held as Part of EvoStar 2021, Virtual Event, April 7–9, 2021, Proceedings Applications of Evolutionary Computation (EvoApplications 2021) Applications of Evolutionary Computation (EvoApplications 2021), Apr 2021, Sevilla (on line), Spain. pp.601-617, ⟨10.1007/978-3-030-72699-7_38⟩ Applications of Evolutionary Computation ISBN: 9783030726980 EvoApplications |
| بيانات النشر: | HAL CCSD, 2021. |
| سنة النشر: | 2021 |
| مصطلحات موضوعية: | FOS: Computer and information sciences, Mathematical optimization, Optimization problem, Automated Algorithm Selection, Computer science, Black-Box Optimization, Computer Science - Neural and Evolutionary Computing, Contrast (statistics), Sampling (statistics), Feature selection, 0102 computer and information sciences, 02 engineering and technology, Function (mathematics), [INFO.INFO-NE]Computer Science [cs]/Neural and Evolutionary Computing [cs.NE], 01 natural sciences, Latin hypercube sampling, 010201 computation theory & mathematics, Feature (computer vision), 0202 electrical engineering, electronic engineering, information engineering, Trajectory, 020201 artificial intelligence & image processing, Neural and Evolutionary Computing (cs.NE), Performance Regression, Feature Selection, Exploratory Landscape Analysis |
| الوصف: | Black-box optimization is a very active area of research, with many new algorithms being developed every year. This variety is needed, on the one hand, since different algorithms are most suitable for different types of optimization problems. But the variety also poses a meta-problem: which algorithm to choose for a given problem at hand? Past research has shown that per-instance algorithm selection based on exploratory landscape analysis (ELA) can be an efficient mean to tackle this meta-problem. Existing approaches, however, require the approximation of problem features based on a significant number of samples, which are typically selected through uniform sampling or Latin Hypercube Designs. The evaluation of these points is costly, and the benefit of an ELA-based algorithm selection over a default algorithm must therefore be significant in order to pay off. One could hope to by-pass the evaluations for the feature approximations by using the samples that a default algorithm would anyway perform, i.e., by using the points of the default algorithm's trajectory. We analyze in this paper how well such an approach can work. Concretely, we test how accurately trajectory-based ELA approaches can predict the final solution quality of the CMA-ES after a fixed budget of function evaluations. We observe that the loss of trajectory-based predictions can be surprisingly small compared to the classical global sampling approach, if the remaining budget for which solution quality shall be predicted is not too large. Feature selection, in contrast, did not show any advantage in our experiments and rather led to worsened prediction accuracy. The inclusion of state variables of CMA-ES only has a moderate effect on the prediction accuracy. Comment: To appear in the Proceedings of EvoAPP 2021 |
| اللغة: | English |
| ردمك: | 978-3-030-72698-0 |
| URL الوصول: | https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2a383dde96ec32e9d0a1041168afb982 https://hal.sorbonne-universite.fr/hal-03233699/document |
| حقوق: | OPEN |
| رقم الأكسشن: | edsair.doi.dedup.....2a383dde96ec32e9d0a1041168afb982 |
| قاعدة البيانات: | OpenAIRE |
| ردمك: | 9783030726980 |
|---|