Adaptive Prediction and Estimation in Linear Regression with Infinitely Many Parameters
Goldenshluger, A. ; Tsybakov, A.
Ann. Statist., Tome 29 (2001) no. 2, p. 1601-1619 / Harvested from Project Euclid
The problem of adaptive prediction and estimation in the stochastic linear regression model with infinitely many parameters is considered.We suggest a prediction method that is sharp asymptotically minimax adaptive over ellipsoids in $\ell_2$. The method consists in an application of blockwise Stein’s rule with “weakly” geometrically increasing blocks to the penalized least squares fits of the first $N$ coefficients. To prove the results we develop oracle inequalities for a sequence model with correlated data.
Publié le : 2001-12-14
Classification:  Linear regression with infinitely many parameters,  adaptive prediction,  exact asyptotics of minimax risk,  blockwise Stein’s rule,  oracle inequalities,  62G05,  62G20
@article{1015345956,
     author = {Goldenshluger, A. and Tsybakov, A.},
     title = {Adaptive Prediction and Estimation in Linear Regression with
			 Infinitely Many Parameters},
     journal = {Ann. Statist.},
     volume = {29},
     number = {2},
     year = {2001},
     pages = { 1601-1619},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1015345956}
}
Goldenshluger, A.; Tsybakov, A. Adaptive Prediction and Estimation in Linear Regression with
			 Infinitely Many Parameters. Ann. Statist., Tome 29 (2001) no. 2, pp.  1601-1619. http://gdmltest.u-ga.fr/item/1015345956/