Model selection by resampling penalization

arXivmath/0701542MaRDI QIDQ6478645FDOQ6478645

Authors: Sylvain Arlot 

Publication date: 19 January 2007

Abstract: We present a new family of model selection algorithms based on the resampling heuristics. It can be used in several frameworks, do not require any knowledge about the unknown law of the data, and may be seen as a generalization of local Rademacher complexities and $V$-fold cross-validation. In the case example of least-square regression on histograms, we prove oracle inequalities, and that these algorithms are naturally adaptive to both the smoothness of the regression function and the variability of the noise level. Then, interpretating $V$-fold cross-validation in terms of penalization, we enlighten the question of choosing $V$. Finally, a simulation study illustrates the strength of resampling penalization algorithms against some classical ones, in particular with heteroscedastic data.

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Nonparametric statistical resampling methods (62G09)

This page was built for publication: Model selection by resampling penalization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6478645)