Reducing algorithm configuration spaces for efficient search
Uloženo v:
| Název: | Reducing algorithm configuration spaces for efficient search |
|---|---|
| Autoři: | Fernando Freitas, Pavel Brazdil, Carlos Soares |
| Zdroj: | International Journal of Data Science and Analytics. 20:4973-4993 |
| Informace o vydavateli: | Springer Science and Business Media LLC, 2025. |
| Rok vydání: | 2025 |
| Popis: | Many current AutoML platforms include a very large space of alternatives (the configuration space). This increases the probability of including the best one for any dataset but makes the task of identifying it for a new dataset more difficult. In this paper, we explore a method that can reduce a large configuration space to a significantly smaller one and so help to reduce the search time for the potentially best algorithm configuration, with limited risk of significant loss of predictive performance. We empirically validate the method with a large set of alternatives based on five ML algorithms with different sets of hyperparameters and one preprocessing method (feature selection). Our results show that it is possible to reduce the given search space by more than one order of magnitude, from a few thousands to a few hundred items. After reduction, the search for the best algorithm configuration is about one order of magnitude faster than on the original space without significant loss in predictive performance. |
| Druh dokumentu: | Article |
| Jazyk: | English |
| ISSN: | 2364-4168 2364-415X |
| DOI: | 10.1007/s41060-025-00764-5 |
| Rights: | CC BY |
| Přístupové číslo: | edsair.doi...........b9e91f1bbff6a112ee9b0f857a45ae02 |
| Databáze: | OpenAIRE |
Full Text Finder 
Nájsť tento článok vo Web of Science | Abstrakt: | Many current AutoML platforms include a very large space of alternatives (the configuration space). This increases the probability of including the best one for any dataset but makes the task of identifying it for a new dataset more difficult. In this paper, we explore a method that can reduce a large configuration space to a significantly smaller one and so help to reduce the search time for the potentially best algorithm configuration, with limited risk of significant loss of predictive performance. We empirically validate the method with a large set of alternatives based on five ML algorithms with different sets of hyperparameters and one preprocessing method (feature selection). Our results show that it is possible to reduce the given search space by more than one order of magnitude, from a few thousands to a few hundred items. After reduction, the search for the best algorithm configuration is about one order of magnitude faster than on the original space without significant loss in predictive performance. |
|---|---|
| ISSN: | 23644168 2364415X |
| DOI: | 10.1007/s41060-025-00764-5 |