Abstract
We consider a heteroscedastic sequence space setup with polynomially increasing variances of observations that allows to treat a number of inverse problems, in particular multivariate ones. We propose an adaptive estimator that attains simultaneously exact asymptotic minimax constants on every ellipsoid of functions within a wide scale (that includes ellipoids with polynomially and exponentially decreasing axes) and, at the same time, satisfies asymptotically exact oracle inequalities within any class of linear estimates having monotone non-increasing weights. The construction of the estimator is based on a properly penalized blockwise Stein's rule, with weakly geometically increasing blocks. As an application, we construct sharp adaptive estimators in the problems of deconvolution and tomography.
| Original language | English |
|---|---|
| Pages (from-to) | 323-354 |
| Number of pages | 32 |
| Journal | Probability Theory and Related Fields |
| Volume | 123 |
| Issue number | 3 |
| DOIs | |
| Publication status | Published - 1 Jul 2002 |
Keywords
- Adaptive curve estimation
- Deconvolution
- Exact minimax constants
- Oracle inequalities
- Statistical inverse problems
- Tomography
Fingerprint
Dive into the research topics of 'Sharp adaptation for inverse problems with random noise'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver