Geodesic
Nonlinear estimation in anisotropic multiindex denoising. Sparse case
Teoriâ veroâtnostej i ee primeneniâ, Tome 52 (2007) no. 1, pp. 150-171 Cet article a éte moissonné depuis la source Math-Net.Ru

Voir la notice de l'article

In dimension one, it has long been observed that the minimax rates of convergences in the scale of Besov spaces present essentially two regimes (and a boundary): dense and the sparse zones. In this paper, we consider the problem of denoising a function depending on a multidimensional variable (for instance, an image), with anisotropic constraints of regularity (especially providing a possible disparity of the inhomogeneous aspect in different directions). The case of the dense zone has been investigated in the former paper [G. Kerkyacharian, O. Lepski, and D. Picard, Probab. Theory Related Fields, 121 (2001), pp. 137–170]. Here, our aim is to investigate the case of the sparse region. This case is more delicate in some aspects. For instance, it was an open question to decide whether this sparse case, in the $d$-dimensional context, has to be split into different regions corresponding to different minimax rates. We will see here that the answer is negative: we still observe a sparse region but with a unique minimax behavior, except, as usual, on the boundary. It is worthwhile to notice that our estimation procedure admits the choice of its parameters under which it is adaptive up to logarithmic factor in the “dense case” [G. Kerkyacharian, O. Lepski, and D. Picard, Probab. Theory Related Fields, 121 (2001), pp. 137–170] and minimax adaptive in the “sparse case”. It is also interesting to observe that in the sparse case the embedding properties of the spaces are fundamental.
Keywords: nonparametric estimation, denoising, anisotropic smoothness, minimax rate of convergence
Mots-clés : anisotropic Besov spaces. 
@article{TVP_2007_52_1_a8,
     author = {G. Kerkyacharian and O. V. Lepskiǐ and D. Picard},
     title = {Nonlinear estimation in anisotropic multiindex denoising. {Sparse} case},
     journal = {Teori\^a vero\^atnostej i ee primeneni\^a},
     pages = {150--171},
     year = {2007},
     volume = {52},
     number = {1},
     language = {en},
     url = {http://geodesic.mathdoc.fr/item/TVP_2007_52_1_a8/}
}
TY  - JOUR
AU  - G. Kerkyacharian
AU  - O. V. Lepskiǐ
AU  - D. Picard
TI  - Nonlinear estimation in anisotropic multiindex denoising. Sparse case
JO  - Teoriâ veroâtnostej i ee primeneniâ
PY  - 2007
SP  - 150
EP  - 171
VL  - 52
IS  - 1
UR  - http://geodesic.mathdoc.fr/item/TVP_2007_52_1_a8/
LA  - en
ID  - TVP_2007_52_1_a8
ER  - 
%0 Journal Article
%A G. Kerkyacharian
%A O. V. Lepskiǐ
%A D. Picard
%T Nonlinear estimation in anisotropic multiindex denoising. Sparse case
%J Teoriâ veroâtnostej i ee primeneniâ
%D 2007
%P 150-171
%V 52
%N 1
%U http://geodesic.mathdoc.fr/item/TVP_2007_52_1_a8/
%G en
%F TVP_2007_52_1_a8
G. Kerkyacharian; O. V. Lepskiǐ; D. Picard. Nonlinear estimation in anisotropic multiindex denoising. Sparse case. Teoriâ veroâtnostej i ee primeneniâ, Tome 52 (2007) no. 1, pp. 150-171. http://geodesic.mathdoc.fr/item/TVP_2007_52_1_a8/

[1] Donoho D. L., Johnstone I. M., Kerkyacharian G., Picard D., “Wavelet shrinkage: asymptopia? (With discussion and a reply by the authors.)”, J. Roy. Statist. Soc., Ser. B, 57:2 (1995), 301–369 | MR | Zbl

[2] Härdle W., Kerkyacharian G., Picard D., Tsybakov A., Wavelets, Approximation, and Statistical Applications, Lecture Notes in Statist., 129, Springer-Verlag, New York, 1998, 265 pp. | MR | Zbl

[3] Ibragimov I. A., Khasminskii R. Z., “Otsenka maksimalnogo znacheniya signala v gaussovskom belom shume”, Matem. zametki, 32:4 (1982), 529–536 | MR

[4] Ingster Yu. I., “Asymptotically minimax hypothesis testing for nonparametric alternatives. I, II, III”, Math. Methods Statist., 2:2 (1993), 85–114 ; 3, 171–189 ; 4, 249–268 | MR | Zbl | MR | Zbl | MR | Zbl

[5] Kerkyacharian G., Lepski O., Picard D., “Nonlinear estimation in anisotropic multi-index denoising”, Probab. Theory Related Fields, 121:2 (2001), 137–170 | DOI | MR | Zbl

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

[7] Lepskii O. V., “Asimptoticheski minimaksnoe adaptivnoe otsenivanie. I: Verkhnie granitsy. Optimalno adaptivnye otsenki”, Teoriya veroyatn. i ee primen., 36:4 (1991), 645–659 | MR

[8] Lepskii O. V., “On problems of adaptive estimation in white Gaussian noise”, Adv. Soviet Math., 12 (1992), 87–106 | MR

[9] Lepskii O. V., “Ob otsenivanii maksimuma neparametricheskogo signala s tochnostyu do postoyannoi”, Teoriya veroyatn. i ee primen., 38:1 (1993), 187–194 | MR

[10] Lepski O. V., Mammen E., Spokoiny V. G., “Optimal spatial adaptation to inhomogeneous smoothness: an approach based on kernel estimates with variable bandwidth selectors”, Ann. Statist., 25:3 (1997), 929–947 | DOI | MR | Zbl

[11] Lepski O. V., Tsybakov A. B., “Asymptotically exact nonparametric hypothesis testing in sup-norm and at a fixed point”, Probab. Theory Related Fields, 117:1 (2000), 17–48 | DOI | MR | Zbl

[12] Nemirovskii A. S., “Neparametricheskoe otsenivanie gladkikh funktsii regressii”, Izv. AN SSSR, ser. tekhn. kibernet., 1985, no. 3, 50–60

[13] Nikolskii S. M., Priblizhenie funktsii mnogikh peremennykh i teoremy vlozheniya, Nauka, M., 1977, 455 pp. | MR

[14] Nussbaum M., “Spline smoothing in regression models and asymptotic efficiency in $L_2$”, Ann. Statist., 13:3 (1985), 984–997 | DOI | MR | Zbl

[15] Nussbaum M., “O neparametricheskom otsenivanii funktsii regressii, gladkoi v oblasti iz $R^k$”, Teoriya veroyatn. i ee primen., 31:1 (1986), 118–125 | MR

[16] Walsh J. B., “An introduction to stochastic partial differential equations”, Lecture Notes in Math., 1180, 1984, 265–439 | MR