Abstract
This paper aims to present some results on the asymptotic behaviour of a matrix associated with certain types of spline functions and shows how these results can be used to obtain a fast algorithm for choosing the smoothing parameter in the smoothing of noisy data by splines.
First, we give a general theorem on the behaviour of the eigenvalues associated with a spline function. The spline functions considered here are those defined by a variational formulation (for general theorems on these splines see [1], [11]).
Second, we use the preceding results to obtain an O(n) — algorithm to calculate the optimal smoothing polynomial spline using the generalized Cross-Validation Technique, in the case of equally spaced data. We obtain an O(n2) algorithm to perform this calculation in the case of non equally spaced data. Some very good numerical results are presented and a table of run times is given. We then introduce a method which calculates the solution (smoothed data) by a piecewise smoothing and correction technique. This method allows us to treat a very important amount of data.
We show too, how calculations can be made with two dimensional data (with arbitrary data points) and generalize the piecewise calculations to this case. We also present a set of numerical results and a table of run times.
Keywords
- Null Space
- Spline Function
- Thin Plate Spline
- Polynomial Spline
- Preceding Subsection
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
This is a preview of subscription content, access via your institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
Bibliographie
ATTEIA M. "Théorie et Applications de Fonctions Spline en Analyse Numérique" Thèse. Grenoble (1966)
BABUSKA I & AZIZ A.K. "Foundations of the Finite Element Method with applications to Partial Differential Equations" Edited by A.K. AZIZ Academic Press, New York (1972)
CHATELIN F. "Théorie de l’Approximation des Opérateurs Linéaires. Application au Calcul des Valeurs Propres d’Operateurs Differentiels et Integraux". Cours de DEA d’Analyse Numérique. Université Scientifique et Médicale de Grenoble (1966)
COURANT R. & HILBERT D. "Methods of Mathematical Physics" Vol I. Interscience Publischers, New York (1953)
CRAVEN P. & WAHBA G. "Smoothing Noisy Data with Spline Functions. Estimating the Correct Degree of Smoothing by the Method of Generalized Cross-Validation" Numerische Mathematik 31, 317–403 (1979)
DUCHON J. "Fonctions Spline à Energie Invariante par Rotation" Rapport de Recherche no 27 U.S.M.G. Grenoble (1976)
DUCHON J. "Interpolation des Fonctions de Deux Variables par des Fonctions Spline du Type Plaque Mince" R.A.I.R.O. Analyse Numérique. Vol 10-no 12 (1976) pp 5–12
FIX G. "Effects of Quadrature Errors in Finite Element Approximation of Steady State, Eigenvalue and Parabolic Problems" in "Foundations of the Finite Element Method with Applications to Partial Differential Equations" Edited by AZIZ A.K. Academic Press, New York (1972)
GOLUB G., HEATH M. & WAHBA G. "Generalized Cross-Validation as a Method for Choosing a Good Ridge Parameter" Technical Report no 491 May 1977 University of Winsconsin Madison.
KREISS H.O. "Difference Approximations for Boundary and Eigenvalue Problems for Ordinary Differential Equations" Mathematics of Computations, Vol 26, 1972, pp 605–624
LAURENT P.J. "Approximation et Optimisation" Hermman, Paris, 1972
NECAS J. "Les Méthodes Directes en Théorie des Equations Elliptiques" Masson, Paris, 1967
PAIHUA L. "Quelques Méthodes Numériques pour les Fonctions Spline à une et deux Variables" Thèse Grenoble. Mai 1978
PAIHUA L. & UTRERAS F. "Un Ensemble de Programmes pour l’Interpolation de Fonctions, par des Fonctions Spline du Type Plaque Mince" Rapport de Recherche no 140. Octobre 1978. IRMA Grenoble.
SCHWARTZ L. "Théorie des Distributions" Hermman, Paris, 1966.
SCHWARZ H.R. "Tridiagonalization of a Symmetric Band Matrix" in "Linear Algebra" Edited by J.H. WILKINSON et C. REINSCH Springer-Verlag. Berlin 1971
THOMMAN J. "Determination et Construction de Fonctions Spline à Deux Variables Définies sur un Domaine Rectangulaire ou Circulaire" Thèse Lille 1970.
UTRERAS F. "Sur le Choix du Paramètre d’Ajustement dans le Lissage par Fonctions Spline" Séminaire d’Analyse Numérique no 296 Grenoble Mars 1978.
UTRERASF. "Sur le Choix du Paramètre d’Ajustement dans le Lissage par Fonctions Spline" Exposé au Colloque National d’Analyse Numérique de France. Giens, le 21 Mai 1978 soumis pour publication.
UTRERAS F. "Utilisation des Programmes de Calcul du Paramètre d’Ajustement dans le Lissage par Fonctions Spline" Rapport de Recherche no 121 — Grenoble Mai 1978.
UTRERAS F. "Quelques Résultats d’Optimalité pour la Méthode de Validation Croisée" Séminaire d’Analyse Numérique no 301 Grenoble Novembre 1978
UTRERAS F. "Utilisation de la Méthode de Validation Croisée pour le Lissage par Fonctions Spline à une ou deux Variables" Doctoral Disertation. Université Scientifique et Médicale de Grenoble. Grenoble Mai 1979.
WAHBA G. "Practical Approximate Solutions to Linear Operator Equations when the Data are Noisy" SIAM Journal on Numerical Analysis — Vol 14 — no 4 Sept. 1977.
WAHBA G. "Smoothing Noisy Data with Spline Functions" Numerische Mathematik 24 (1975) pp 383–393
WAHBA G. "Optimal Smoothing of Density Estimates" in Classification and Clustering, J. VAN RYZIN ed., 423–458, Academic Press (1977)
WAHBA G. & WOLD S. "A Completely Automatic French Curve: Fitting Spline Functions by Cross-Validation" Comm. Statistics 4, 1–7, 1975.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1979 Springer-Verlag
About this paper
Cite this paper
Utreras, F. (1979). Cross-validation techniques for smoothing spline functions in one or two dimensions. In: Gasser, T., Rosenblatt, M. (eds) Smoothing Techniques for Curve Estimation. Lecture Notes in Mathematics, vol 757. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0098498
Download citation
DOI: https://doi.org/10.1007/BFb0098498
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-09706-8
Online ISBN: 978-3-540-38475-5
eBook Packages: Springer Book Archive
