On universal oracle inequalities related to high-dimensional linear models
Golubev, Yuri
Ann. Statist., Tome 38 (2010) no. 1, p. 2751-2780 / Harvested from Project Euclid
This paper deals with recovering an unknown vector θ from the noisy data Y = Aθ + σξ, where A is a known (m × n)-matrix and ξ is a white Gaussian noise. It is assumed that n is large and A may be severely ill-posed. Therefore, in order to estimate θ, a spectral regularization method is used, and our goal is to choose its regularization parameter with the help of the data Y. For spectral regularization methods related to the so-called ordered smoothers [see Kneip Ann. Statist. 22 (1994) 835–866], we propose new penalties in the principle of empirical risk minimization. The heuristical idea behind these penalties is related to balancing excess risks. Based on this approach, we derive a sharp oracle inequality controlling the mean square risks of data-driven spectral regularization methods.
Publié le : 2010-10-15
Classification:  Spectral regularization,  excess risk,  ordered smoother,  empirical risk minimization,  oracle inequality,  62C10,  62C10,  62G05
@article{1279638539,
     author = {Golubev, Yuri},
     title = {On universal oracle inequalities related to high-dimensional linear models},
     journal = {Ann. Statist.},
     volume = {38},
     number = {1},
     year = {2010},
     pages = { 2751-2780},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1279638539}
}
Golubev, Yuri. On universal oracle inequalities related to high-dimensional linear models. Ann. Statist., Tome 38 (2010) no. 1, pp.  2751-2780. http://gdmltest.u-ga.fr/item/1279638539/