Skip to Main content Skip to Navigation
Journal articles

Nonlinear estimation for linear inverse problems with error in the operator

Abstract : We study two nonlinear methods for statistical linear inverse problems when the operator is not known. The two constructions combine Galerkin regularization and wavelet thresholding. Their performances depend on the underlying structure of the operator, quantified by an index of sparsity. We prove their rate-optimality and adaptivity properties over Besov classes.
Document type :
Journal articles
Complete list of metadatas

https://hal-upec-upem.archives-ouvertes.fr/hal-00693076
Contributor : Admin Lama <>
Submitted on : Tuesday, May 1, 2012 - 7:58:26 PM
Last modification on : Thursday, March 19, 2020 - 12:26:02 PM

Links full text

Identifiers

Citation

Marc Hoffmann, Markus Reiss. Nonlinear estimation for linear inverse problems with error in the operator. Annals of Statistics, Institute of Mathematical Statistics, 2008, 36 (1), pp.310--336. ⟨10.1214/009053607000000721⟩. ⟨hal-00693076⟩

Share

Metrics

Record views

535