Arbeitspapier
Convergence rates of general regularization methods for statistical inverse problems and applications
During the past the convergence analysis for linear statistical inverse problems has mainly focused on spectral cut-off and Tikhonov type estimators. Spectral cut-off estimators achieve minimax rates for a broad range of smoothness classes and operators, but their practical usefulness is limited by the fact that they require a complete spectral decomposition of the operator. Tikhonov estimators are simpler to compute, but still involve the inversion of an operator and achieve minimax rates only in restricted smoothness classes. In this paper we introduce a unifying technique to study the mean square error of a large class of regularization methods (spectral methods) including the aforementioned estimators as well as many iterative methods, such as í-methods and the Landweber iteration. The latter estimators converge at the same rate as spectral cut-off, but only require matrixvector products. Our results are applied to various problems, in particular we obtain precise convergence rates for satellite gradiometry, L2-boosting, and errors in variable problems.
- Sprache
-
Englisch
- Erschienen in
-
Series: Technical Report ; No. 2007,04
- Thema
-
Statistical inverse problems
iterative regularization methods
Tikhonov regularization
nonparametric regression
minimax convergence rates
satellite gradiometry
Hilbert scales
boosting
errors in variable
- Ereignis
-
Geistige Schöpfung
- (wer)
-
Bissantz, Nicolai
Hohage, T.
Munk, Axel
Ruymgaart, F.
- Ereignis
-
Veröffentlichung
- (wer)
-
Universität Dortmund, Sonderforschungsbereich 475 - Komplexitätsreduktion in Multivariaten Datenstrukturen
- (wo)
-
Dortmund
- (wann)
-
2007
- Handle
- Letzte Aktualisierung
-
10.03.2025, 11:44 MEZ
Datenpartner
ZBW - Deutsche Zentralbibliothek für Wirtschaftswissenschaften - Leibniz-Informationszentrum Wirtschaft. Bei Fragen zum Objekt wenden Sie sich bitte an den Datenpartner.
Objekttyp
- Arbeitspapier
Beteiligte
- Bissantz, Nicolai
- Hohage, T.
- Munk, Axel
- Ruymgaart, F.
- Universität Dortmund, Sonderforschungsbereich 475 - Komplexitätsreduktion in Multivariaten Datenstrukturen
Entstanden
- 2007
Ähnliche Objekte (12)
Convergence rates of general regularization methods for statistical inverse problems and applications
Convergence rates for variational regularization of statistical inverse problems
Optimal rates for regularization of statistical inverse learning problems
Tikhonov regularization in Hilbert scales for nonlinear statistical inverse problems
Convergence rates for variational regularization of inverse problems in exponential families
Regularization Methods for Statistical Modelling in Small Area Estimation
Adaptive frame based regularization methods for linear ill-posed inverse problems
Regularization Methods in Banach Spaces applied to Inverse Medium Scattering Problems
Numerical regularization for atmospheric inverse problems
Regularization of the inverse medium problem : on nonstandard methods for sparse reconstruction
Regularization of the inverse medium problem : on nonstandard methods for sparse reconstruction
Direct and inverse problems in machine learning : kernel methods and spectral regularization
Convergence rates of general regularization methods for statistical inverse problems and applications
Convergence rates for variational regularization of statistical inverse problems
Optimal rates for regularization of statistical inverse learning problems
Tikhonov regularization in Hilbert scales for nonlinear statistical inverse problems
Convergence rates for variational regularization of inverse problems in exponential families
Regularization Methods for Statistical Modelling in Small Area Estimation
Adaptive frame based regularization methods for linear ill-posed inverse problems
Regularization Methods in Banach Spaces applied to Inverse Medium Scattering Problems
Numerical regularization for atmospheric inverse problems
Regularization of the inverse medium problem : on nonstandard methods for sparse reconstruction
Regularization of the inverse medium problem : on nonstandard methods for sparse reconstruction
Direct and inverse problems in machine learning : kernel methods and spectral regularization
Convergence rates of general regularization methods for statistical inverse problems and applications
Convergence rates for variational regularization of statistical inverse problems
Optimal rates for regularization of statistical inverse learning problems
Tikhonov regularization in Hilbert scales for nonlinear statistical inverse problems
Convergence rates for variational regularization of inverse problems in exponential families
Regularization Methods for Statistical Modelling in Small Area Estimation
Adaptive frame based regularization methods for linear ill-posed inverse problems
Regularization Methods in Banach Spaces applied to Inverse Medium Scattering Problems
Numerical regularization for atmospheric inverse problems
Regularization of the inverse medium problem : on nonstandard methods for sparse reconstruction
Regularization of the inverse medium problem : on nonstandard methods for sparse reconstruction