Compartir
Título
RHOASo: An Early Stop Hyper-Parameter Optimization Algorithm
Autor
Facultad/Centro
Área de conocimiento
Título de la revista
Mathematics
Número de la revista
18
Cita Bibliográfica
Castañeda, Á. L. M., Decastro-García, N., & Escudero García, D. (2021). Rhoaso: An early stop hyper-parameter optimization algorithm. Mathematics, 9(18). https://doi.org/10.3390/MATH9182334
Editorial
MDPI
Fecha
2021-09-20
Resumen
[EN] This work proposes a new algorithm for optimizing hyper-parameters of a machine learning algorithm, RHOASo, based on conditional optimization of concave asymptotic functions. A comparative analysis of the algorithm is presented, giving particular emphasis to two important properties: the capability of the algorithm to work efficiently with a small part of a dataset and to finish the tuning process automatically, that is, without making explicit, by the user, the number of iterations that the algorithm must perform. Statistical analyses over 16 public benchmark datasets comparing the performance of seven hyper-parameter optimization algorithms with RHOASo were carried out. The efficiency of RHOASo presents the positive statistically significant differences concerning the other hyper-parameter optimization algorithms considered in the experiments. Furthermore, it is shown that, on average, the algorithm needs around 70% of the iterations needed by other algorithms to achieve competitive performance. The results show that the algorithm presents significant stability regarding the size of the used dataset partition.
Materia
Palabras clave
Peer review
SI
ID proyecto
- This work was partially supported by the Spanish National Cybersecurity Institute (INCIBE) under contract Art.83, key: X54.
- The authors would like to thank the Spanish National Cybersecurity Institute (INCIBE), who partially supported this work. Additionally, in this research, the resources of the Center of Supercomputation of Castilla y León (SCAYLE) were used.
URI
DOI
Versión del editor
Aparece en las colecciones
- Artículos [4665]
Ficheros en el ítem
Tamaño:
10.11
xmlui.dri2xhtml.METS-1.0.size-megabytes
Formato:
Adobe PDF
Descripción:
Published version