On adaptive inverse estimation of linear functionals in Hilbert scales

We address the problem of estimating the value of a linear functional h f , xi from random noisy observations of y 1⁄4 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.

[1]  Markus Hegland,et al.  Variable hilbert scales and their interpolation inequalities with applications to tikhonov regularization , 1995 .

[2]  D. Donoho,et al.  Renormalization Exponents and Optimal Pointwise Rates of Convergence , 1992 .

[3]  Andreas Neubauer,et al.  On Converse and Saturation Results for Tikhonov Regularization of Linear Ill-Posed Problems , 1997 .

[4]  Peter Mathé,et al.  Optimal Discretization of Inverse Problems in Hilbert Scales. Regularization and Self-Regularization of Projection Methods , 2000, SIAM J. Numer. Anal..

[5]  A. Tsybakov,et al.  Sharp adaptation for inverse problems with random noise , 2002 .

[6]  O. Lepskii,et al.  Asymptotically minimax adaptive estimation. II: Schemes without optimal adaptation: adaptive estimators , 1993 .

[7]  D. Donoho.  Statistical Estimation and Optimal Recovery , 1994 .

[8]  I. A. Ibragimov,et al.  Estimation of Linear Functionals in Gaussian Noise , 1988 .

[9]  A. V. Skorohod,et al.  Integration in Hilbert Space , 1974 .

[10]  Henryk Wozniakowski,et al.  Information-based complexity , 1987, Nature.

[11]  Bernard A. Mair,et al.  Statistical Inverse Estimation in Hilbert Scales , 1996, SIAM J. Appl. Math..

[12]  O. Lepskii.  Asymptotically Minimax Adaptive Estimation. I: Upper Bounds. Optimally Adaptive Estimates , 1992 .

[13]  A. Goldenshluger,et al.  Adaptive estimation of linear functionals in Hilbert scales from indirect white noise observations , 2000 .

[14]  L. Brown,et al.  A constrained risk inequality with applications to nonparametric functional estimation , 1996 .

[15]  V. V. Petrov,et al.  Limit Theorems of Probability Theory , 2000 .

[16]  Sergei V. Pereverzev,et al.  The degree of ill-posedness in stochastic and deterministic noise models , 2005 .

[17]  V. Statulevičius,et al.  Limit Theorems of Probability Theory , 2000 .

[18]  Andreas Neubauer,et al.  An a Posteriori Parameter Choice for Tikhonov Regularization in Hilbert Scales Leading to Optimal Convergence Rates , 1988 .

[19]  O. Lepskii.  On a Problem of Adaptive Estimation in Gaussian White Noise , 1991 .

[20]  N. Vakhania,et al.  Probability Distributions on Banach Spaces , 1987 .

[21]  W. R. van Zwet,et al.  Asymptotic Efficiency of Inverse Estimators , 2000 .

[22]  Y. Brudnyi,et al.  Interpolation of linear operators , 2002 .

[23]  H. Woxniakowski.  Information-Based Complexity , 1988 .

[24]  Ulrich Tautenhahn,et al.  Error Estimates for Regularization Methods in Hilbert Scales , 1996 .

[25]  F. Natterer.  Error bounds for tikhonov regularization in hilbert scales , 1984 .

[26]  I. Ibragimov,et al.  On Nonparametric Estimation of the Value of a Linear Functional in Gaussian White Noise , 1985 .