Nonparametric independent component analysis
Samarov, Alexander ; Tsybakov, Alexandre
Bernoulli, Tome 10 (2004) no. 2, p. 565-582 / Harvested from Project Euclid
We consider the problem of nonparametric estimation of a d-dimensional probability density and its `principal directions' in the independent component analysis model. A new method of estimation based on diagonalization of nonparametric estimates of certain matrix functionals of the density is suggested. We show that the proposed estimators of principal directions are $\sqrt{n}$ -consistent and that the corresponding density estimators converge at the optimal rate.
Publié le : 2004-08-14
Classification:  estimation of functionals,  independent component analysis,  nonparametric density estimation,  projection pursuit
@article{1093265630,
     author = {Samarov, Alexander and Tsybakov, Alexandre},
     title = {Nonparametric independent component analysis},
     journal = {Bernoulli},
     volume = {10},
     number = {2},
     year = {2004},
     pages = { 565-582},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1093265630}
}
Samarov, Alexander; Tsybakov, Alexandre. Nonparametric independent component analysis. Bernoulli, Tome 10 (2004) no. 2, pp.  565-582. http://gdmltest.u-ga.fr/item/1093265630/