Skip to main content

Sampling and Stability

  • Conference paper

Part of the Lecture Notes in Computer Science book series (LNTCS,volume 5862)

Abstract

In Numerical Analysis one often has to conclude that an error function is small everywhere if it is small on a large discrete point set and if there is a bound on a derivative. Sampling inequalities put this onto a solid mathematical basis.

A stability inequality is similar, but holds only on a finite–dimensional space of trial functions. It allows bounding a trial function by a norm on a sufficiently fine data sample, without any bound on a high derivative.

This survey first describes these two types of inequalities in general and shows how to derive a stability inequality from a sampling inequality plus an inverse inequality on a finite–dimensional trial space. Then the state–of–the–art in sampling inequalities is reviewed, and new extensions involving functions of infinite smoothness and sampling operators using weak data are presented.

Finally, typical applications of sampling and stability inequalities for recovery of functions from scattered weak or strong data are surveyed. These include Support Vector Machines and unsymmetric methods for solving partial differential equations.

Keywords

  • Radial Basis Function
  • Trial Function
  • Sampling Operator
  • Lebesgue Constant
  • Trial Space

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

Chapter
USD   29.95
Price excludes VAT (USA)
  • DOI: 10.1007/978-3-642-11620-9_23
  • Chapter length: 23 pages
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
eBook
USD   99.00
Price excludes VAT (USA)
  • ISBN: 978-3-642-11620-9
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
Softcover Book
USD   129.00
Price excludes VAT (USA)

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Agadzhanov, A.: Functional properties of Sobolev spaces of infinite order. Soviet. Math. Dokl. 38, 88–92 (1989)

    MathSciNet  MATH  Google Scholar 

  2. Arcangéli, R., López de Silanes, M., Torrens, J.: An extension of a bound for functions in Sobolev spaces, with applications to (m, s)-spline interpolation and smoothing. Numer. Math. 107, 181–211 (2007)

    MathSciNet  CrossRef  MATH  Google Scholar 

  3. Arcangéli, R., López de Silanes, M., Torrens, J.: Estimates for functions in Sobolev spaces defined on unbounded domains. To appear in Journal of Approximation Theory (2009), doi:10.1016/j.jat.2008.09.001

    Google Scholar 

  4. Atluri, S., Shen, S.: The meshless local Petrov-Galerkin (MLPG) method: A simple and less-costly alternative to the Finite Element and Boundary Element methods. Computer Modeling in Engineering and Sciences 3, 11–51 (2002)

    MathSciNet  MATH  Google Scholar 

  5. Atluri, S., Shen, S.: The meshless local Petrov-Galerkin (MLPG) method. Tech Science Press, Encino (2002)

    MATH  Google Scholar 

  6. Borwein, P., Erdelyi, T.: Polynomials and Polynomial Inequalities. Springer, New York (1995)

    CrossRef  MATH  Google Scholar 

  7. Brenner, S.C., Scott, L.R.: The mathematical theory of finite element methods. Texts in Applied Mathematics, vol. 15. Springer, New York (1994)

    MATH  Google Scholar 

  8. Caponnetto, A., DeVito, E.: Optimal rates for the regularized least-squares algorithm. Foundations of Computational Mathematics 7, 331–368 (2007)

    MathSciNet  CrossRef  MATH  Google Scholar 

  9. Caponnetto, A., DeVito, E.: Learning and approximation by Gaussians on Riemannian manifolds. Advances in Computational Mathematics 29, 291–310 (2008)

    MathSciNet  CrossRef  Google Scholar 

  10. Corrigan, A., Wallin, J., Wanner, T.: A sampling inequality for fractional order Sobolev semi-norms using arbitrary order data. Preprint, available online via arXiv:0801.4097v2

    Google Scholar 

  11. Cucker, F., Smale, S.: On the mathematical foundations of Learning. Bulletin of the AMS 39, 1–49 (2001)

    MathSciNet  CrossRef  MATH  Google Scholar 

  12. Cucker, F., Zhou, D.-X.: Learning Theory: An Approximation Theory Viewpoint. Cambridge University Press, Cambridge (2007)

    CrossRef  MATH  Google Scholar 

  13. De Marchi, S., Schaback, R.: Stability of kernel-based interpolation. To appear in Advances in Computational Mathematics (2008), doi:10.1007/s10444-008-9093-4

    Google Scholar 

  14. Duchon, J.: Sur l’erreur d’interpolation des fonctions de plusieurs variables pas les D m–splines. Rev. Française Automat. Informat. Rech. Opér. Anal. Numer. 12, 325–334 (1978)

    MATH  Google Scholar 

  15. Girosi, F.: An Equivalence Between Sparse Approximation and Support Vector Machines. Neural Computation 10, 1455–1480 (1998)

    CrossRef  Google Scholar 

  16. Haroske, D.D., Triebel, H.: Distributions, Sobolev spaces, elliptic equations. EMS Textbooks in Mathematics. European Mathematical Society (EMS), Zürich (2008)

    Google Scholar 

  17. Jetter, K., Stöckler, J., Ward, J.D.: Norming sets and scattered data approximation on spheres. In: Approximation Theory IX. Computational Aspects, vol. II, pp. 137–144 (1998)

    Google Scholar 

  18. Jetter, K., Stöckler, J., Ward, J.D.: Error estimates for scattered data interpolation on spheres. Mathematics of Computation 68, 733–747 (1999)

    MathSciNet  CrossRef  MATH  Google Scholar 

  19. Madych, W.R.: An estimate for multivariate interpolation II. Journal of Approximation Theory 142, 116–128 (2006)

    MathSciNet  CrossRef  MATH  Google Scholar 

  20. Micchelli, C.A., Pontil, M.: Learning the kernel function via regularization. Journal of Machine Learning Research 6, 1099–1125 (2005)

    MathSciNet  MATH  Google Scholar 

  21. Narcowich, F.J., Ward, J.D., Wendland, H.: Sobolev bounds on functions with scattered zeros, with applications to radial basis function surface fitting. Mathematics of Computation 74, 743–763 (2005)

    MathSciNet  CrossRef  MATH  Google Scholar 

  22. Poggio, T., Smale, S.: The Mathematics of Learning: Dealing with Data. Notices of the AMS 50, 537–544 (2003)

    MathSciNet  MATH  Google Scholar 

  23. Raju, I., Phillips, D., Krishnamurthy, T.: A radial basis function approach in the meshless local Petrov-Galerkin method for Euler-Bernoulli beam problems. Computational Mechanics 34, 464–474 (2004)

    CrossRef  MATH  Google Scholar 

  24. Rieger, C.: Sampling Inequalities and Applications. PhD thesis, Universität Göttingen (2008)

    Google Scholar 

  25. Rieger, C., Zwicknagl, B.: Deterministic error analysis of kernel-based regression and related kernel based algorithms. To appear in Journal of Machine Learning Research (2009)

    Google Scholar 

  26. Rieger, C., Zwicknagl, B.: Sampling inequalities for infinitely smooth functions, with applications to interpolation and machine learning. To appear in Advances in Computational Mathematics (2009), doi:10.1007/s10444-008-9089-0

    Google Scholar 

  27. Schaback, R.: Convergence of Unsymmetric Kernel-Based Meshless Collocation Methods. SIAM J. Numer. Anal. 45, 333–351 (2007)

    MathSciNet  CrossRef  MATH  Google Scholar 

  28. Schaback, R.: Recovery of functions from weak data using unsymmetric meshless kernel-based methods. Applied Numerical Mathematics 58, 726–741 (2007)

    MathSciNet  CrossRef  MATH  Google Scholar 

  29. Schaback, R., Wendland, H.: Inverse and saturation theorems for radial basis function interpolation. Math. Comp. 71, 669–681 (2002)

    MathSciNet  CrossRef  MATH  Google Scholar 

  30. Schaback, R., Wendland, H.: Kernel techniques: from machine learning to meshless methods. Acta Numerica 15, 543–639 (2006)

    MathSciNet  CrossRef  MATH  Google Scholar 

  31. Schölkopf, B., Smola, A.: Learning with Kernels. MIT Press, Cambridge (2002)

    MATH  Google Scholar 

  32. Schölkopf, B., Williamson, R.C., Bartlett, P.L.: New Support Vector Algorithms. Neural Computation 12, 1207–1245 (2000)

    CrossRef  Google Scholar 

  33. Smale, S., Zhou, D.: Estimating the approximation error in learning theory. Analysis and Applications 1, 1–25 (2003)

    MathSciNet  CrossRef  MATH  Google Scholar 

  34. Vapnik, V.: The nature of statistical learning theory. Springer, New York (1995)

    CrossRef  MATH  Google Scholar 

  35. Wahba, G.: Spline Models for Observational Data. CBMS-NSF Regional Conference Series in Applied Mathematics, vol. 59. SIAM, Philadelphia (1990)

    CrossRef  MATH  Google Scholar 

  36. Wendland, H.: On the convergence of a general class of finite volume methods. SIAM Journal of Numerical Analysis 43, 987–1002 (2005)

    MathSciNet  CrossRef  MATH  Google Scholar 

  37. Wendland, H.: Scattered Data Approximation. Cambridge Monographs on Applied and Computational Mathematics. Cambridge University Press, Cambridge (2005)

    MATH  Google Scholar 

  38. Wendland, H., Rieger, C.: Approximate interpolation with applications to selecting smoothing parameters. Numer. Math. 101, 643–662 (2005)

    MathSciNet  CrossRef  MATH  Google Scholar 

  39. Wu, Z.M.: Hermite–Birkhoff interpolation of scattered data by radial basis functions. Approximation Theory and its Applications 8, 1–10 (1992)

    MathSciNet  MATH  Google Scholar 

  40. Zhang, Y.: Convergence of meshless Petrov-Galerkin method using radial basis functions. Applied Mathematics and Computation 183, 307–321 (2006)

    MathSciNet  CrossRef  MATH  Google Scholar 

  41. Zwicknagl, B.: Power series kernels. Constructive Approximation 29, 61–84 (2009)

    MathSciNet  CrossRef  MATH  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and Permissions

Copyright information

© 2010 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Rieger, C., Schaback, R., Zwicknagl, B. (2010). Sampling and Stability. In: Dæhlen, M., Floater, M., Lyche, T., Merrien, JL., Mørken, K., Schumaker, L.L. (eds) Mathematical Methods for Curves and Surfaces. MMCS 2008. Lecture Notes in Computer Science, vol 5862. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-11620-9_23

Download citation

  • DOI: https://doi.org/10.1007/978-3-642-11620-9_23

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-642-11619-3

  • Online ISBN: 978-3-642-11620-9

  • eBook Packages: Computer ScienceComputer Science (R0)