Abstract
The data driven extrapolation requires the definition of a functional model depending on the available data and has the application scope of providing reliable predictions on the unknown dynamics. Since data might be scattered, we drive our attention towards kernel models that have the advantage of being meshfree. Precisely, the proposed numerical method makes use of the so-called Variably Scaled Kernels (VSKs), which are introduced to implement a feature augmentation-like strategy based on discrete data. Due to the possible uncertainty on the data and since we are interested in modelling the behaviour of the target functions, we seek for a regularized solution by ridge regression. Focusing on polyharmonic splines, we investigate their implementation in the VSK setting and we provide error bounds in Beppo–Levi spaces. The performances of the method are then tested on functions showing exponential or rational decay. Comparisons with Support Vector Regression (SVR) are also carried out and highlight that the proposed approach is effective, particularly since it does not require to train complex architecture constructions.
Similar content being viewed by others
Notes
Tests have been carried out on a Intel(R) Core(TM) i7 CPU 4712MQ 2.13 GHz processor.
References
Bakas, N.P.: Numerical solution for the extrapolation problem of analytic functions. Research 2019(6), 1–10 (2019)
Beatson, R., Bui, H.Q., Levesley, J.: Embeddings of Beppo-Levi spaces in Hölder-Zygmund spaces, and a new method for radial basis function interpolation error estimates. J. Approx. Theo. 137(2), 166–178 (2005)
Beatson, R., Light, W.: Quasi-interpolation by thin-plate splines on a square. Const. Approx. 9, 407–433 (1993)
Bozzini, M., Lenarduzzi, L., Rossini, M., Schaback, R.: Interpolation with variably scaled kernels. IMA J. Numer. Anal. 35(1), 199–219 (2015)
Campagna, R., Bayona, V., Cuomo, S.: Using local PHS+poly approximations for Laplace Transform Inversion by Gaver-Stehfest algorithm. Dolomit. Res. Notes Approx. 13, 55–64 (2020)
Campagna, R., Conti, C.: Penalized hyperbolic-polynomial splines. Appl. Math. Lett. 118, 107159 (2021)
Campagna, R., Conti, C., Cuomo, S.: Smoothing exponential-polynomial splines for multiexponential decay data. Dolomit. Res. Notes Approx. 12, 86–100 (2019)
Campagna, R., Conti, C., Cuomo, S.: Computational error bounds for Laplace transform inversion based on smoothing splines. Appl. Math. Comput. 383, 125376 (2020)
Campagna, R., Conti, C., Cuomo, S.: A procedure for Laplace transform inversion based on smoothing exponential-polynomial splines. In: Sergeyev, Y.D., Kvasov, D.E. (eds.) Numerical Computations: Theory and Algorithms, pp. 11–18. Springer, Cham (2020)
Campagna, R., Cuomo, S., De Marchi, S., Perracchione, E., Severino, G.: A stable meshfree pde solver for source-type flows in porous media. Appl. Numer. Math. 149, 30–42 (2020)
Campi, C., Marchetti, F., Perracchione, E.: Learning via Variably Scaled Kernels (VSKs). Adv. Comput. Math. (2021) (to appear)
Candès, E.J., Fernandez-Granda, C.: Towards a mathematical theory of super-resolution. Commun. Pure Appl. Math. 67(6), 906–956 (2014)
Charina, M., Conti, C., Sauer, T.: Regularity of multivariate vector subdivision schemes. Numer. Algor. 39, 97–113 (2005)
de Boor, C., Fix, G.: Spline approximation by quasiinterpolants. J. Approx. Theory 8(1), 19–45 (1973)
De Marchi, S., Erb, W., Marchetti, F., Perracchione, E., Rossini, M.: Shape-driven interpolation with discontinuous kernels: Error analysis, edge extraction, and applications in magnetic particle imaging. SIAM J. Sci. Comput. 42(2), B472–B491 (2020)
De Marchi, S., Marchetti, F., Perracchione, E.: Jumping with variably scaled discontinuous kernels (VSDKs). BIT Numer. Math. 60, 441–463 (2020)
Demanet, L., Townsend, A.: Stable extrapolation of analytic functions. Found. Comput. Math. 9, 297–331 (2019)
Deny, J., Lions, J.: Les espaces du type de Beppo Levi. Annal. Inst. Four. 5, 302–370 (1954)
Duchon, J.: Interpolation des fonctions de deux variables suivant le principe de la flexion des plaques minces. ESAIM Math. Model. Numer. Anal. Modélisation Mathématique et Analyse Numérique 10(R3), 5–12 (1976)
Fasshauer, G.E.: Meshfree Approximation Methods with MATLAB. World Scientific, Singapore (2007)
Fasshauer, G.E., McCourt, M.: Kernel-based Approximation Methods using MATLAB. World Scientific, Singapore (2015)
Gao, W., Fasshauer, G.E., Sun, X., Zhou, X.: Optimality and regularization properties of quasi-interpolation: deterministic and stochastic approaches. SIAM J. Numer. Anal. 58(4), 2059–2078 (2020)
Harder, R., Desmarais, R.: Interpolation using surface splines. J. Aircr. 9(2), 189–191 (1972)
Holland, P.W., Welsch, R.E.: Robust regression using iteratively reweighted least-squares. Commun. Stat. Theo. Methods 6(9), 813–827 (1977)
Iske, A.: On the approximation order and numerical stability of local lagrange interpolation by polyharmonic splines. In: Haussmann, W., Jetter, K., Reimer, M., Stöckler, J. (eds.) Modern Developments in Multivariate Approximation, pp. 153–165. Birkhäuser Basel, Basel (2003)
Li, W., Duan, L., Xu, D., Tsang, I.W.: Learning with augmented features for supervised and semi-supervised heterogeneous domain adaptation. IEEE Trans. Pattern Anal. Mach. Intell. 36(6), 1134–1148 (2014)
Mirzargar, M., Ryan, J., Kirby, R.: Smoothness-Increasing Accuracy-Conserving (SIAC) filtering and quasi-interpolation: A unified view. J. Sci. Comput. 67(1), 237–261 (2016)
Nocedal, J., Wright, S.J.: Numerical Optimization. Springer, New York (2006)
Powell, M.: The uniform convergence of thin plate spline interpolation in two dimensions. Numer. Math. 68(1), 107–128 (1994)
Romani, L., Rossini, M., Schenone, D.: Edge detection methods based on RBF interpolation. J. Comput. Appl. Math. 349, 532–547 (2019)
Romano, A., Campagna, R., Masi, P., Toraldo, G.: NMR data analysis of water mobility in wheat flour dough: A computational approach. In: Sergeyev, Y.D., Kvasov, D.E. (eds.) Numerical Computations: Theory and Algorithms, pp. 146–157. Springer, Cham (2020)
Schaback, R.: Error estimates and condition numbers for radial basis function interpolation. Adv. Comput. Math. 3, 251–264 (1995)
Schölkopf, B., Smola, A.J.: Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond. Adaptive Computation and Machine Learning. MIT Press, Cambridge (2002)
Seber, G., Wild, C.: Nonlinear Regression. Wiley-Interscience, Hoboken (2003)
Shawe-Taylor, J., Cristianini, N.: Kernel Methods for Pattern Analysis. Cambridge University Press, Cambridge (2004)
Shetty, S., White, P.: Curvature-continuous extensions for rational B-spline curves and surfaces. Comput. Aided Des. 23(7), 484–491 (1991)
Wahba, G.: Spline Models for Observational Data. Society for Industrial and Applied Mathematics, Philadelphia (1990)
Wendland, H.: Scattered Data Approximation. Cambridge University Press, Cambridge Monographs on Applied and Computational Mathematics (2004)
Acknowledgements
This research has been accomplished within the Research ITalian network on Approximation (RITA) and partially funded by the ASI - INAF grant “Artificial Intelligence for the analysis of solar FLARES data (AI-FLARES)”. The authors are members of the GNCS IN\(\delta \)AM Research group. We sincerely thank the reviewers for helping us to significantly improve the manuscript
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Campagna, R., Perracchione, E. Data-Driven Extrapolation Via Feature Augmentation Based on Variably Scaled Thin Plate Splines. J Sci Comput 88, 15 (2021). https://doi.org/10.1007/s10915-021-01526-8
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s10915-021-01526-8
Keywords
- Data-driven extrapolation
- Feature augmentation
- Radial basis functions
- Variably scaled kernels
- Thin plate splines
- Ridge regression