Skip to main content
SpringerLink
Log in

Penalized Model Selection for Ill-Posed Linear Problems

  • Chapter
Recent Advances in Applied Probability

  • 1412 Accesses

Abstract

In this article we review the problem of discretization-regularization for inverse linear ill-posed problems from a statistical point of view. We discuss the problem in the context of adaptive model selection and relate these results to Bayesian estimation.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 84.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 169.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info
Hardcover Book
USD 109.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Aluffi-Pentini et al. (1999) J Optim. Th. & Appl. Vol 103,p 45–64.

    MATH  MathSciNet  Google Scholar 

  2. Baraud, Y. Model selection for regression on a fixed design.Probab. Theory Relat. Fields 117,467–493(2000)

    MATH  MathSciNet  Google Scholar 

  3. A. Barron, L. Birgé & P. Massart. (1999). Risk bounds for model selection via penalization. Probab. Theory Related Fields. Vol. 113(3), p. 301–413.

    Article  MathSciNet  Google Scholar 

  4. L. Birgé & P. Massart. (1998) Minimum contrast estimators on sieves: exponential bounds and rates of convergence. Bernoulli. Vol. 4(3), p. 329–375.

    MathSciNet  Google Scholar 

  5. L. Birgé & P. Massart.(2001) Gaussian model selection. J. Eur. math Soc. 3, p. 203–268.

    Google Scholar 

  6. L. Birgé & P. Massart. (2001a). A generalized Cp criterion for Gaussian model selection. Preprint.

    Google Scholar 

  7. Cavalier, L and Tsybakov, A.B. Sharp adaptation for inverse problems with random noise. Preprint. (2000).

    Google Scholar 

  8. Cavalier, L., Golubev, G.K., Picard, D. and Tsybakov, A.B. Oracle inequalities for inverse problems. Preprint (2000).

    Google Scholar 

  9. D. Donoho & I. Johnstone. (1994) ideal spatial adaptation via wavelet shrinkage. Biometrika, vol 81, p. 425–455.

    MathSciNet  Google Scholar 

  10. D. Donoho. (1995) Nonlinear solution of linear inverse problems by wavelet-vaguelette decomposition. J. of Appl. and Comput. Harmonic Analysis. Vol. 2(2), p. 101–126.

    MATH  MathSciNet  Google Scholar 

  11. H.W. Engl & W. Grever. (1994) Using the L-curve foe determining optimal regularization parameters, Numer. Math. Vol. 69, p. 25–31.

    Article  MathSciNet  Google Scholar 

  12. A. Frommer & P. Maass. (1999) Fast CG-based methods for Tikhonov-Phillips regularization. SIAM J. Sci. Comput. Vol 20(5), p. 1831–1850.

    Article  MathSciNet  Google Scholar 

  13. F. Gamboa & E. Gassiat. (1997) Bayesian methods for ill-posed problems. The Annals of Statistics. Vol. 25, p. 328–350.

    MathSciNet  Google Scholar 

  14. F. Gamboa. (1999) New Bayesian Methods for Ill Posed problems. Statistics & Decisions, 17, p. 315–337

    MATH  MathSciNet  Google Scholar 

  15. Goldenshluger, A. and Tsybakov, A. Adaptive prediction and estimation in linear regression with infinitely many parameters. Preprint (2001).

    Google Scholar 

  16. Grenander, Ulf. (1981) Abstract inference. Wiley Series in Probability and Mathematical Statistics. New York etc.: John Wiley & Sons.

    Google Scholar 

  17. C. Han & B. Carlin. (2000) MCMC methods for computing Bayes factors. A comparative review. Preprint.

    Google Scholar 

  18. J. Kaliffa; S. Mallat. (2001) Thresholding estimators for inverse problems and deconvolutions. To appear in Annals of Stat.

    Google Scholar 

  19. J. Kaliffa; S. Mallat. (2001a) Thresholding estimators for inverse problems and deconvolutions. To appear in Annals of Stat.

    Google Scholar 

  20. M. Kilmer & D. O’Leary. (2001) Choosing regularization parameters in iterative methods for ill posed problems. SIAM-J. Matrix-Anal.-Appl. Vol 22(4),p. 1204–1221.

    MathSciNet  Google Scholar 

  21. Lavielle, M. On the use of penalized contrasts for solving inverse problems. Application to the DDC problem. Preprint (2001).

    Google Scholar 

  22. J.M. Loubés. (2001) Adaptive bayesian estimation. Preprint.

    Google Scholar 

  23. J.M. Loubés & S. Van de Geer. (2001). Adaptive estimation in regression, using soft thresholding type penalties. Preprint.

    Google Scholar 

  24. P. Maass, S. Pereverzev, R. Ramlau & S. Solodky. (2001). An adaptive discretization forTikhonov-Phillips regularization with a posteriori parameter selection. Numer. Math.. Vol. 87(3), p. 485–502.

    MathSciNet  Google Scholar 

  25. Massart, P. Some applications of concentration inequalities to statistics. Annales de la Faculté des Sciences de Toulouse Vol. IX(2), 245–303 (2000).

    MathSciNet  Google Scholar 

  26. A. Neubauer (1988). An a posteriori parameter choice for Tikhonov regularization in the presence of modelling error. Appl. Numer. Math. Vol. 4(6),p. 507–519.

    Article  MATH  MathSciNet  Google Scholar 

  27. F. O’sullivan. (1986) A statistical perspective on ill-posed inverse problems. Statistical Science. Vol. 1(4), p. 502–527.

    MathSciNet  Google Scholar 

  28. Tsybakov, A.B. Adaptive estimation for inverse problems: a logarithmic effect in L2. Preprint (2000).

    Google Scholar 

  29. S.G. Solodky. (1999) Optimization of Projection methods for linear ill-posed problems. Computational Mathematics and Mathematical Physics. Vol 39(2), p. 185–193.

    MathSciNet  Google Scholar 

  30. M. Pinsker. (1980) Optimal filtering of square integrable signals in Gaussian white noise. Problems Inform. Transmission. Vol. 16, p. 120–133.

    MATH  Google Scholar 

  31. Tikhonov, Andrey N.; Arsenin, Vasiliy Y. Solutions of ill-posed problems. Translation editor Frity John. (English) Scripta Series in Mathematics. New York etc.: John Wiley & Sons; Washington, D.C. 1977

    Google Scholar 

  32. V. Vapnik. (1998) Statistical Learning Theory, John Wiley, NY.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Instituto Venezolano de Investigaciones Científicas, Venezuela

    Carenne Ludeña

  2. Facutad de Ciencias. Escuela de Matemáticas, Universidad Central de Venezuela, Venezuela

    Ricardo Ríos

Authors
  1. Carenne Ludeña
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ricardo Ríos
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Universidad de Chile, Chile

    Ricardo Baeza-Yates

  2. University of Connecticut, USA

    Joseph Glaz

  3. Universidad Simón Bolívar, Venezuela

    Henryk Gzyl  & José Luis Palacios  & 

  4. University of Bern, Switzerland

    Jürgen Hüsler

Rights and permissions

Reprints and permissions

Copyright information

© 2005 Springer Science + Business Media, Inc.

About this chapter

Cite this chapter

Ludeña, C., Ríos, R. (2005). Penalized Model Selection for Ill-Posed Linear Problems. In: Baeza-Yates, R., Glaz, J., Gzyl, H., Hüsler, J., Palacios, J.L. (eds) Recent Advances in Applied Probability. Springer, Boston, MA. https://doi.org/10.1007/0-387-23394-6_14

Download citation

Publish with us

Policies and ethics

Search

Navigation