مؤتمر
Tuning as a Means of Assessing the Benefits of New Ideas in Interplay with Existing Algorithmic Modules
| العنوان: | Tuning as a Means of Assessing the Benefits of New Ideas in Interplay with Existing Algorithmic Modules |
|---|---|
| المؤلفون: | de Nobel, Jacob, Vermetten, Diederick, Wang, Hao, Doerr, Carola, Bäck, Thomas |
| المساهمون: | Leiden Institute of Advanced Computer Science Leiden (LIACS), Universiteit Leiden = Leiden University, Centre National de la Recherche Scientifique (CNRS), Recherche Opérationnelle (RO), LIP6, Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS), Sorbonne Université (SU) |
| المصدر: | Genetic and Evolutionary Computation Conference (GECCO 2021, Companion Material, Workshop) ; https://hal.sorbonne-universite.fr/hal-03233951Test ; Genetic and Evolutionary Computation Conference (GECCO 2021, Companion Material, Workshop), Jul 2021, Lille (en ligne), France. ⟨10.1145/3449726.3463167⟩ |
| بيانات النشر: | HAL CCSD |
| سنة النشر: | 2021 |
| مصطلحات موضوعية: | [INFO.INFO-NE]Computer Science [cs]/Neural and Evolutionary Computing [cs.NE] |
| جغرافية الموضوع: | Lille (en ligne), France |
| الوصف: | International audience ; Introducing new algorithmic ideas is a key part of the continuous improvement of existing optimization algorithms. However, when introducing a new component into an existing algorithm, assessing its potential benefits is a challenging task. Often, the component is added to a default implementation of the underlying algorithm and compared against a limited set of other variants. This assessment ignores any potential interplay with other algorithmic ideas that share the same base algorithm, which is critical in understanding the exact contributions being made. We explore a more extensive procedure, which uses hyperparameter tuning as a means of assessing the benefits of new algorithmic components. This allows for a more robust analysis by not only focusing on the impact on performance, but also by investigating how this performance is achieved. We implement our suggestion in the context of the Modular CMA-ES framework, which was redesigned and extended to include some new modules and several new options for existing modules, mostly focused on the step-size adaptation method. Our analysis highlights the differences between these new modules, and identifies the situations in which they have the largest contribution. |
| نوع الوثيقة: | conference object |
| اللغة: | English |
| العلاقة: | info:eu-repo/semantics/altIdentifier/arxiv/2102.12905; hal-03233951; https://hal.sorbonne-universite.fr/hal-03233951Test; https://hal.sorbonne-universite.fr/hal-03233951/documentTest; https://hal.sorbonne-universite.fr/hal-03233951/file/modCMAES%20GECCO%20workshop.pdfTest; ARXIV: 2102.12905 |
| DOI: | 10.1145/3449726.3463167 |
| الإتاحة: | https://doi.org/10.1145/3449726.3463167Test https://hal.sorbonne-universite.fr/hal-03233951Test https://hal.sorbonne-universite.fr/hal-03233951/documentTest https://hal.sorbonne-universite.fr/hal-03233951/file/modCMAES%20GECCO%20workshop.pdfTest |
| حقوق: | info:eu-repo/semantics/OpenAccess |
| رقم الانضمام: | edsbas.444BFD50 |
| قاعدة البيانات: | BASE |
| DOI: | 10.1145/3449726.3463167 |
|---|