Geodesic
Block thresholding and sharp adaptive estimation in severely ill-posed inverse problems
Teoriâ veroâtnostej i ee primeneniâ, Tome 48 (2003) no. 3, pp. 534-556 Cet article a éte moissonné depuis la source Math-Net.Ru

Voir la notice de l'article

We consider the problem of solving linear operator equations from noisy data under the assumptions that the singular values of the operator decrease exponentially fast and that the underlying solution is also exponentially smooth in the Fourier domain. We suggest an estimator of the solution based on a running version of block thresholding in the space of Fourier coefficients. This estimator is shown to be sharp adaptive to the unknown smoothness of the solution.
Keywords: linear operator equation, white Gaussian noise, adaptive estimation, running block thresholding. 
@article{TVP_2003_48_3_a5,
     author = {L. Cavalier and Yu. F. Golubev and O. V. Lepskiǐ and A. Tsybakov},
     title = {Block thresholding and sharp adaptive estimation in severely ill-posed inverse problems},
     journal = {Teori\^a vero\^atnostej i ee primeneni\^a},
     pages = {534--556},
     year = {2003},
     volume = {48},
     number = {3},
     language = {en},
     url = {http://geodesic.mathdoc.fr/item/TVP_2003_48_3_a5/}
}
TY  - JOUR
AU  - L. Cavalier
AU  - Yu. F. Golubev
AU  - O. V. Lepskiǐ
AU  - A. Tsybakov
TI  - Block thresholding and sharp adaptive estimation in severely ill-posed inverse problems
JO  - Teoriâ veroâtnostej i ee primeneniâ
PY  - 2003
SP  - 534
EP  - 556
VL  - 48
IS  - 3
UR  - http://geodesic.mathdoc.fr/item/TVP_2003_48_3_a5/
LA  - en
ID  - TVP_2003_48_3_a5
ER  - 
%0 Journal Article
%A L. Cavalier
%A Yu. F. Golubev
%A O. V. Lepskiǐ
%A A. Tsybakov
%T Block thresholding and sharp adaptive estimation in severely ill-posed inverse problems
%J Teoriâ veroâtnostej i ee primeneniâ
%D 2003
%P 534-556
%V 48
%N 3
%U http://geodesic.mathdoc.fr/item/TVP_2003_48_3_a5/
%G en
%F TVP_2003_48_3_a5
L. Cavalier; Yu. F. Golubev; O. V. Lepskiǐ; A. Tsybakov. Block thresholding and sharp adaptive estimation in severely ill-posed inverse problems. Teoriâ veroâtnostej i ee primeneniâ, Tome 48 (2003) no. 3, pp. 534-556. http://geodesic.mathdoc.fr/item/TVP_2003_48_3_a5/

[1] Bakushinskii A. B., “O postroenii regulyarizuyuschikh algoritmov pri sluchainykh pomekhakh”, Dokl. AN SSSR, 189:2 (1969), 231–233

[2] Cavalier L., Golubev G. K., Picard D., Tsybakov A. B., “Oracle inequalities for inverse problems”, Ann. Statist., 30:3 (2002), 843–874 | DOI | MR | Zbl

[3] Cavalier L., Tsybakov A. B., “Sharp adaptation for inverse problems with random noise”, Probab. Theory Relat. Fields, 123:3 (2002), 323–354 | DOI | MR | Zbl

[4] Efromovich S., “Robust and efficient recovery of a signal passed through a filter and then contaminated by nonGaussian noise”, IEEE Trans. Inf. Theory, 43:4 (1997), 1184–1191 | DOI | MR | Zbl

[5] Efromovich S., Koltchinskii V., “On inverse problems with unknown operators”, IEEE Trans. Inform. Theory, 47:7 (2001), 2876–2893 | DOI | MR

[6] Ermakov M. S., “Minimax estimation of the solution of an ill-posed convolution type problem”, Problemy peredachi informatsii, 25:3 (1989), 28–39 | MR

[7] Goldenshluger A., Pereverzev S. V., “Adaptive estimation of linear functionals in Hilbert scales from indirect white noise observations”, Probab. Theory Relat. Fields, 118:2 (2000), 169–186 | DOI | MR | Zbl

[8] Golubev G. K., Khasminskii P. Z., “Statisticheskii podkhod k nekotorym obratnym zadacham dlya uravnenii v chastnykh proizvodnykh”, Problemy peredachi informatsii, 35:2 (1999), 51–66 | MR | Zbl

[9] Golubev G. K., Khasminskii R. Z., “A statistical approach to the Cauchy problem for the Laplace equation”, State of the Art in Probability and Statistics, Festschrift for Willem R. van Zwet, IMS Lecture Notes Monograph Series, 36, eds. M. de Gunst, C. Klaassen, A. van der Vaart, IMS, Institute of Mathematical Statistics, Beachwood, OH, 2000, 419–433 | MR

[10] Hall P., Kerkyacharian G., Picard D., “Block threshold rules for curve estimation using kernel and wavelet methods”, Ann. Statist., 26:3 (1998), 922–942 | DOI | MR | Zbl

[11] Johnstone I. M., “Wavelet shrinkage for correlated data and inverse problems: Adaptivity results”, Statistica Sinica, 9:1 (1999), 51–83 | MR | Zbl

[12] Lepskii O. V., “Ob odnoi zadache adaptivnogo otsenivaniya v gaussovskom belom shume”, Teoriya veroyatn. i ee primen., 35:3 (1990), 459–470 | MR

[13] Mair B., Ruymgaart F. H., “Statistical inverse estimation in Hilbert scales”, SIAM J. Appl. Math., 56:5 (1996), 1424–1444 | DOI | MR | Zbl

[14] Mathé P., Pereverzev S. V., Optimal discretization and degrees of ill-posedness for inverse estimation in Hilbert scales in the presence of random noise, Preprint 469, WIAS, Berlin

[15] Natterer F., “Error bounds for Tikhonov regularization in Hilbert scales”, Appl. Anal., 18 (1984), 29–37 | DOI | MR | Zbl

[16] Pensky M., Vidakovic B., “Adaptive wavelet estimator for nonparametric density deconvolution”, Ann. Statist., 27:6 (1999), 2033–2053 | DOI | MR | Zbl

[17] Sudakov B. H., Khalfin L. A., “Statisticheskii podkhod k korrektnosti zadach matematicheskoi fiziki”, Dokl. AN SSSR, 157:5 (1964), 1058–1060 | MR | Zbl

[18] Tsybakov A. B., “Pointwise and sup-norm sharp adaptive estimation of functions on the Sobolev classes”, Ann. Statist., 26 (1998), 2420–2469 | DOI | MR | Zbl

[19] Tsybakov A. B., “On the best rate of adaptive estimation in some inverse problems”, C. R. Acad. Sci. Paris, Math. Ser. I, 330 (2000), 835–840 | MR | Zbl