Nonlinear estimation for linear inverse problems with error in the operator - Archive ouverte HAL Access content directly
Journal Articles Annals of Statistics Year : 2008

Nonlinear estimation for linear inverse problems with error in the operator

Markus Reiss
  • Function : Author

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.

Dates and versions

hal-00693076 , version 1 (01-05-2012)

Identifiers

Cite

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

Altmetric

Share

Gmail Facebook Twitter LinkedIn More