Cet article traite du problème de l’estimation d’une fonction
We consider the problem of estimating a function
Mots-clés : curve estimation, model selection, composite functions, adaptation, single index model, artificial neural networks, gaussian mixtures
@article{AIHPB_2014__50_1_285_0, author = {Baraud, Yannick and Birg\'e, Lucien}, title = {Estimating composite functions by model selection}, journal = {Annales de l'I.H.P. Probabilit\'es et statistiques}, pages = {285--314}, publisher = {Gauthier-Villars}, volume = {50}, number = {1}, year = {2014}, doi = {10.1214/12-AIHP516}, mrnumber = {3161532}, zbl = {1281.62093}, language = {en}, url = {https://www.numdam.org/articles/10.1214/12-AIHP516/} }
TY - JOUR AU - Baraud, Yannick AU - Birgé, Lucien TI - Estimating composite functions by model selection JO - Annales de l'I.H.P. Probabilités et statistiques PY - 2014 SP - 285 EP - 314 VL - 50 IS - 1 PB - Gauthier-Villars UR - https://www.numdam.org/articles/10.1214/12-AIHP516/ DO - 10.1214/12-AIHP516 LA - en ID - AIHPB_2014__50_1_285_0 ER -
%0 Journal Article %A Baraud, Yannick %A Birgé, Lucien %T Estimating composite functions by model selection %J Annales de l'I.H.P. Probabilités et statistiques %D 2014 %P 285-314 %V 50 %N 1 %I Gauthier-Villars %U https://www.numdam.org/articles/10.1214/12-AIHP516/ %R 10.1214/12-AIHP516 %G en %F AIHPB_2014__50_1_285_0
Baraud, Yannick; Birgé, Lucien. Estimating composite functions by model selection. Annales de l'I.H.P. Probabilités et statistiques, Tome 50 (2014) no. 1, pp. 285-314. doi : 10.1214/12-AIHP516. https://www.numdam.org/articles/10.1214/12-AIHP516/
[1] Adaptation to anisotropy and inhomogeneity via dyadic piecewise polynomial selection. Math. Methods Statist. 21 (2012) 1-28. | MR
.[2] Estimator selection with respect to Hellinger-type risks. Probab. Theory Related Fields 151 (2011) 353-401. | MR
.[3] Model selection for (auto-)regression with dependent data. ESAIM Probab. Stat. 5 (2001) 33-49. | Numdam | MR | Zbl
, and .[4] Gaussian model selection with an unknown variance. Ann. Statist. 37 (2009) 630-672. | MR | Zbl
, and .[5] Risk bounds for model selection via penalization. Probab. Theory Related Fields 113 (1999) 301-413. | MR | Zbl
, and .[6] Universal approximation bounds for superpositions of a sigmoidal function. IEEE Trans. Inform. Theory 39 (1993) 930-945. | MR | Zbl
.[7] Approximation and estimation bounds for artificial neural networks. Machine Learning 14 (1994) 115-133. | Zbl
.[8] Model selection via testing: An alternative to (penalized) maximum likelihood estimators. Ann. Inst. Henri Poincaré Probab. Stat. 42 (2006) 273-325. | Numdam | MR
.[9] Model selection for Poisson processes. In Asymptotics: Particles, Processes and Inverse Problems, Festschrift for Piet Groeneboom 32-64. E. Cator, G. Jongbloed, C. Kraaikamp, R. Lopuhaä and J. Wellner (Eds). IMS Lecture Notes - Monograph Series 55. Inst. Math. Statist., Beachwood, OH, 2007. | MR | Zbl
.
[10] Model selection for density estimation with
[11] Gaussian model selection. J. Eur. Math. Soc. (JEMS) 3 (2001) 203-268. | MR | Zbl
and .[12] Multidimensional spline approximation. SIAM J. Numer. Anal. 17 (1980) 380-402. | MR | Zbl
, and .[13] Constructive Approximation. Springer, Berlin, 1993. | MR | Zbl
and .[14] A projection pursuit algorithm for exploratory data analysis. IEEE Trans. Comput. C-23 (1974) 881-890. | Zbl
and .[15] Wavelet characterizations for anisotropic Besov spaces. Appl. Comput. Harmon. Anal. 12 (2002) 179-208. | MR | Zbl
.[16] Rate-optimal estimation for a general class of nonparametric regression models with unknown link functions. Ann. Statist. 35 (2007) 2589-2619. | MR | Zbl
and .[17] Projection pursuit (with discussion). Ann. Statist. 13 (1985) 435-525. | MR | Zbl
.[18] Nonparametric estimation of composite functions. Ann. Statist. 37 (2009) 1360-1404. | MR | Zbl
, and .[19] A non asymptotic penalized criterion for Gaussian mixture model selection. ESAIM Probab. Stat. 15 (2011) 41-68. | Numdam | MR
and .[20] Optimal global rates of convergence for nonparametric regression. Ann. Statist. 10 (1982) 1040-1053. | MR | Zbl
.Cité par Sources :