An Efficient Algorithm for Ill-Conditioned Separable Nonlinear Least Squares

For separable nonlinear least squares models, a variable projection algorithm based on matrix factorization is studied, and the ill-conditioning of the model parameters is considered in the specific solution process of the model. When the linear parameters are estimated, the Tikhonov regularization...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Jiayan Wang, Lanlan Guo, Zongmin Li, Xueqin Wang, Zhengqing Fu
Formato: article
Lenguaje:EN
Publicado: Hindawi Limited 2021
Materias:
Acceso en línea:https://doaj.org/article/58a480ee03124b70b800323b7d0e3bef
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:58a480ee03124b70b800323b7d0e3bef
record_format dspace
spelling oai:doaj.org-article:58a480ee03124b70b800323b7d0e3bef2021-11-22T01:09:58ZAn Efficient Algorithm for Ill-Conditioned Separable Nonlinear Least Squares2314-478510.1155/2021/7625175https://doaj.org/article/58a480ee03124b70b800323b7d0e3bef2021-01-01T00:00:00Zhttp://dx.doi.org/10.1155/2021/7625175https://doaj.org/toc/2314-4785For separable nonlinear least squares models, a variable projection algorithm based on matrix factorization is studied, and the ill-conditioning of the model parameters is considered in the specific solution process of the model. When the linear parameters are estimated, the Tikhonov regularization method is used to solve the ill-conditioned problems. When the nonlinear parameters are estimated, the QR decomposition, Gram–Schmidt orthogonalization decomposition, and SVD are applied in the Jacobian matrix. These methods are then compared with the method in which the variables are not separated. Numerical experiments are performed using RBF neural network data, and the experimental results are analyzed in terms of both qualitative and quantitative indicators. The results show that the proposed algorithms are effective and robust.Jiayan WangLanlan GuoZongmin LiXueqin WangZhengqing FuHindawi LimitedarticleMathematicsQA1-939ENJournal of Mathematics, Vol 2021 (2021)
institution DOAJ
collection DOAJ
language EN
topic Mathematics
QA1-939
spellingShingle Mathematics
QA1-939
Jiayan Wang
Lanlan Guo
Zongmin Li
Xueqin Wang
Zhengqing Fu
An Efficient Algorithm for Ill-Conditioned Separable Nonlinear Least Squares
description For separable nonlinear least squares models, a variable projection algorithm based on matrix factorization is studied, and the ill-conditioning of the model parameters is considered in the specific solution process of the model. When the linear parameters are estimated, the Tikhonov regularization method is used to solve the ill-conditioned problems. When the nonlinear parameters are estimated, the QR decomposition, Gram–Schmidt orthogonalization decomposition, and SVD are applied in the Jacobian matrix. These methods are then compared with the method in which the variables are not separated. Numerical experiments are performed using RBF neural network data, and the experimental results are analyzed in terms of both qualitative and quantitative indicators. The results show that the proposed algorithms are effective and robust.
format article
author Jiayan Wang
Lanlan Guo
Zongmin Li
Xueqin Wang
Zhengqing Fu
author_facet Jiayan Wang
Lanlan Guo
Zongmin Li
Xueqin Wang
Zhengqing Fu
author_sort Jiayan Wang
title An Efficient Algorithm for Ill-Conditioned Separable Nonlinear Least Squares
title_short An Efficient Algorithm for Ill-Conditioned Separable Nonlinear Least Squares
title_full An Efficient Algorithm for Ill-Conditioned Separable Nonlinear Least Squares
title_fullStr An Efficient Algorithm for Ill-Conditioned Separable Nonlinear Least Squares
title_full_unstemmed An Efficient Algorithm for Ill-Conditioned Separable Nonlinear Least Squares
title_sort efficient algorithm for ill-conditioned separable nonlinear least squares
publisher Hindawi Limited
publishDate 2021
url https://doaj.org/article/58a480ee03124b70b800323b7d0e3bef
work_keys_str_mv AT jiayanwang anefficientalgorithmforillconditionedseparablenonlinearleastsquares
AT lanlanguo anefficientalgorithmforillconditionedseparablenonlinearleastsquares
AT zongminli anefficientalgorithmforillconditionedseparablenonlinearleastsquares
AT xueqinwang anefficientalgorithmforillconditionedseparablenonlinearleastsquares
AT zhengqingfu anefficientalgorithmforillconditionedseparablenonlinearleastsquares
AT jiayanwang efficientalgorithmforillconditionedseparablenonlinearleastsquares
AT lanlanguo efficientalgorithmforillconditionedseparablenonlinearleastsquares
AT zongminli efficientalgorithmforillconditionedseparablenonlinearleastsquares
AT xueqinwang efficientalgorithmforillconditionedseparablenonlinearleastsquares
AT zhengqingfu efficientalgorithmforillconditionedseparablenonlinearleastsquares
_version_ 1718418401449213952