Wavelet thresholding for nonnecessarily Gaussian noise: Functionality

Averkamp, R.; Houdré, C.

Ann. Statist., Tome 33 (2005) no. 1, p. 2164-2193 / Harvested from Project Euclid

Résumé

For signals belonging to balls in smoothness classes and noise with enough moments, the asymptotic behavior of the minimax quadratic risk among soft-threshold estimates is investigated. In turn, these results, combined with a median filtering method, lead to asymptotics for denoising heavy tails via wavelet thresholding. Some further comparisons of wavelet thresholding and of kernel estimators are also briefly discussed.

Publié le : 2005-10-14
Classification: Wavelets, thresholding, minimax, 62G07, 62C20, 60G70, 41A25

@article{1132936560,
     author = {Averkamp, R. and Houdr\'e, C.},
     title = {Wavelet thresholding for nonnecessarily Gaussian noise: Functionality},
     journal = {Ann. Statist.},
     volume = {33},
     number = {1},
     year = {2005},
     pages = { 2164-2193},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1132936560}
}

Averkamp, R.; Houdré, C. Wavelet thresholding for nonnecessarily Gaussian noise: Functionality. Ann. Statist., Tome 33 (2005) no. 1, pp.  2164-2193. http://gdmltest.u-ga.fr/item/1132936560/