Adaptive wavelet estimator for nonparametric density deconvolution

The problem of estimating a density g based on a sample X-1, X-2, X-n from p = q * g is considered. Linear and nonlinear wavelet estimators teased on Meyer-type wavelets are constructed. The estimators are asymptotically opti mal and adaptive if g belongs to the Sobolev space H-alpha. Moreover, the e stimators considered in this paper adjust automatically to the situation wh en g is supersmooth.