Functional aggregation for nonparametric regression
Juditsky, Anatoli ; Nemirovski, Arkadii
Ann. Statist., Tome 28 (2000) no. 3, p. 681-712 / Harvested from Project Euclid
We consider the problem of estimating an unknown function $f$ from $N$ noisy observations on a random grid. In this paper we address the following aggregation problem: given $M$ functions $f_1,\dots, f_M$, find an “aggregated ”estimator which approximates $f$ nearly as well as the best convex combination $f^*$ of $f_1,\dots, f_M$. We propose algorithms which provide approximations of $f^*$ with expected $L_2$ accuracy $O(N^{-1/4}\ln^{1/4} M$. We show that this approximation rate cannot be significantly improved. We discuss two specific applications: nonparametric prediction for a dynamic system with output nonlinearity and reconstruction in the Jones – Barron class.
Publié le : 2000-05-14
Classification:  Functional aggregation,  convex optimization,  stochastic approximation,  62G08,  62L20
@article{1015951994,
     author = {Juditsky, Anatoli and Nemirovski, Arkadii},
     title = {Functional aggregation for nonparametric regression},
     journal = {Ann. Statist.},
     volume = {28},
     number = {3},
     year = {2000},
     pages = { 681-712},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1015951994}
}
Juditsky, Anatoli; Nemirovski, Arkadii. Functional aggregation for nonparametric regression. Ann. Statist., Tome 28 (2000) no. 3, pp.  681-712. http://gdmltest.u-ga.fr/item/1015951994/