Indexed by:
Abstract:
This paper studies wavelet estimations for supersmooth density functions with additive noises. We first show lower bounds of L-p risk (1 <= p < infinity) with both moderately and severely ill-posed noises. Then a Shannon wavelet estimator provides optimal or nearly-optimal estimations over L-p risks for p >= 2, and a nearly-optimal result for 1 < p < 2 under both noises. In the nearly-optimal cases, the ratios of upper and lower bounds are determined. When p = 1, we give a nearly-optimal estimation with moderately ill-posed noise by using the Meyer wavelet. Finally, the practical estimators are considered. Our results are motivated by the work of Pensky and Vidakovic (1999), Butucea and Tsybakov (2008), Comte et al. (2006), Lacour (2006) and Lounici and Nickl (2011).
Keyword:
Reprint Author's Address:
Source :
SCIENCE CHINA-MATHEMATICS
ISSN: 1674-7283
Year: 2017
Issue: 10
Volume: 60
Page: 1901-1922
1 . 4 0 0
JCR@2022
ESI Discipline: MATHEMATICS;
ESI HC Threshold:66
CAS Journal Grade:2
Cited Count:
WoS CC Cited Count: 1
SCOPUS Cited Count: 1
ESI Highly Cited Papers on the List: 0 Unfold All
WanFang Cited Count:
Chinese Cited Count:
30 Days PV: 10
Affiliated Colleges: