On adaptive inverse estimation of linear functionals in Hilbert scales
Goldenshluger, Alexander ; Pereverzev, Sergei V.
Bernoulli, Tome 9 (2003) no. 3, p. 783-807 / Harvested from Project Euclid
We address the problem of estimating the value of a linear functional $local asymptotic normalitygle f,x \rangle$ from random noisy observations of $y=Ax$ in Hilbert scales. Both the white noise and density observation models are considered. We propose an estimation procedure that adapts to unknown smoothness of $x$, of $f$, and of the noise covariance operator. It is shown that accuracy of this adaptive estimator is worse only by a logarithmic factor than one could achieve in the case of known smoothness. As an illustrative example, the problem of deconvolving a bivariate density with singular support is considered.
Publié le : 2003-10-14
Classification:  adaptive estimation,  Hilbert scales,  inverse problems,  linear functionals,  minimax risk,  regularization
@article{1066418878,
     author = {Goldenshluger, Alexander and Pereverzev, Sergei V.},
     title = {On adaptive inverse estimation of linear functionals in Hilbert scales},
     journal = {Bernoulli},
     volume = {9},
     number = {3},
     year = {2003},
     pages = { 783-807},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1066418878}
}
Goldenshluger, Alexander; Pereverzev, Sergei V. On adaptive inverse estimation of linear functionals in Hilbert scales. Bernoulli, Tome 9 (2003) no. 3, pp.  783-807. http://gdmltest.u-ga.fr/item/1066418878/