This study introduces the use of Bayesian Optimization (BO) to determine the best shape parameter for Radial Basis Function (RBF) interpolation. The method involves modeling the error function with a Gaussian Process, which iteratively identifies the best shape parameter. This self-updating process significantly reduces search time compared to the Leave One Out Cross Validation (LOOCV) technique.
Radial basis function shape parameter search using bayesian optimization
Cavoretto, Roberto;Rossi, Alessandra De;Lancellotti, Sandro
2025-01-01
Abstract
This study introduces the use of Bayesian Optimization (BO) to determine the best shape parameter for Radial Basis Function (RBF) interpolation. The method involves modeling the error function with a Gaussian Process, which iteratively identifies the best shape parameter. This self-updating process significantly reduces search time compared to the Leave One Out Cross Validation (LOOCV) technique.
File in questo prodotto:
| File | Dimensione | Formato | |
|---|---|---|---|
|
P40.pdf
Accesso aperto
Tipo di file:
PDF EDITORIALE
Dimensione
835.57 kB
Formato
Adobe PDF
|
835.57 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
