|
Problemy Peredachi Informatsii, 2004, Volume 40, Issue 3, Pages 21–32
(Mi ppi140)
|
|
|
|
This article is cited in 2 scientific papers (total in 2 papers)
Methods of Signal Processing
On the Empirical Risk Minimization Method
G. K. Golubevab a Institute for Information Transmission Problems, Russian Academy of Sciences
b Université de Provence
Abstract:
We consider the problem of estimating an unknown vector observed in a simple white Gaussian noise model. For the estimation, a family of projection estimators is used; the problem is to choose, based on observations, the best estimator within this family. The paper studies a method for choosing a projection estimator, based on the principle of penalized empirical risk minimization. For this estimation method, nonasymptotic inequalities controlling its quadratic risk are given.
Received: 24.12.2003 Revised: 31.05.2004
Citation:
G. K. Golubev, “On the Empirical Risk Minimization Method”, Probl. Peredachi Inf., 40:3 (2004), 21–32; Problems Inform. Transmission, 40:3 (2004), 202–211
Linking options:
https://www.mathnet.ru/eng/ppi140 https://www.mathnet.ru/eng/ppi/v40/i3/p21
|
Statistics & downloads: |
Abstract page: | 343 | Full-text PDF : | 156 | References: | 35 |
|