Zobrazeno 1 - 4
of 4
pro vyhledávání: '"AMS 62G08"'
Publikováno v:
[Research Report]-. 2012
ISIT
Journal of Multivariate Analysis
Journal of Multivariate Analysis, Elsevier, 2012, 112, pp.24-34
Journal of Multivariate Analysis, 2012, 112, pp.24-34. ⟨10.1016/j.jmva.2012.05.020⟩
ISIT
Journal of Multivariate Analysis
Journal of Multivariate Analysis, Elsevier, 2012, 112, pp.24-34
Journal of Multivariate Analysis, 2012, 112, pp.24-34. ⟨10.1016/j.jmva.2012.05.020⟩
We propose a new k-NN regression estimate based on a data-dependent metric in Rd which is used to define the k-nearest neighbors of a given point. The metric is invariant under all affine transformations. With this metric, the standard k-nearest neig
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5a8b87819d12604555e9e03ca45467f6
Autor:
Arnak S. Dalalyan, Joseph Salmon
Publikováno v:
Annals of Statistics
Annals of Statistics, Institute of Mathematical Statistics, 2012, 40 (4), pp.2327-2355. ⟨10.1214/12-AOS1038⟩
Ann. Statist. 40, no. 4 (2012), 2327-2355
Annals of Statistics, 2012, 40 (4), pp.2327-2355. ⟨10.1214/12-AOS1038⟩
Annals of Statistics, Institute of Mathematical Statistics, 2012, 40 (4), pp.2327-2355. ⟨10.1214/12-AOS1038⟩
Ann. Statist. 40, no. 4 (2012), 2327-2355
Annals of Statistics, 2012, 40 (4), pp.2327-2355. ⟨10.1214/12-AOS1038⟩
International audience; We consider the problem of combining a (possibly uncountably infinite) set of affine estimators in non-parametric regression model with heteroscedastic Gaussian noise. Focusing on the exponentially weighted aggregate, we prove
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e677f391fd780802b18f9a31197ffa37
http://arxiv.org/abs/1104.3969
http://arxiv.org/abs/1104.3969
Autor:
Arlot, Sylvain
We consider the problem of choosing between several models in least-squares regression with heteroscedastic data. We prove that any penalization procedure is suboptimal when the penalty is a function of the dimension of the model, at least for some t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::076a1d98c2937fc3bb54cc2e1f3c476b
Autor:
Sylvain Arlot
Publikováno v:
Electronic Journal of Statistics
Electronic Journal of Statistics, Shaker Heights, OH : Institute of Mathematical Statistics, 2009, 3, pp.557--624. ⟨10.1214/08-EJS196⟩
Electron. J. Statist. 3 (2009), 557-624
Electronic Journal of Statistics, 2009, 3, pp.557--624. ⟨10.1214/08-EJS196⟩
Electronic Journal of Statistics, Shaker Heights, OH : Institute of Mathematical Statistics, 2009, 3, pp.557--624. ⟨10.1214/08-EJS196⟩
Electron. J. Statist. 3 (2009), 557-624
Electronic Journal of Statistics, 2009, 3, pp.557--624. ⟨10.1214/08-EJS196⟩
In this paper, a new family of resampling-based penalization procedures for model selection is defined in a general framework. It generalizes several methods, including Efron's bootstrap penalization and the leave-one-out penalization recently propos
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::007763a88d85186502f2dfdbc24917e4
http://arxiv.org/abs/math/0701542
http://arxiv.org/abs/math/0701542