Skip to main navigation Skip to search Skip to main content

Sharp adaptation for inverse problems with random noise

  • Aix Marseille Université

Research output: Contribution to journal › Article › peer-review

110 Citations (Scopus)

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 languageEnglish
Pages (from-to)323-354
Number of pages32
JournalProbability Theory and Related Fields
Volume123
Issue number3
DOIs
Publication statusPublished - 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