Abstract
We study the problem of aggregation of M arbitrary estimators of a regression function with respect to the mean squared risk. Three main types of aggregation are considered: model selection, convex and linear aggregation. We define the notion of optimal rate of aggregation in an abstract context and prove lower bounds valid for any method of aggregation. We then construct procedures that attain these bounds, thus establishing optimal rates of linear, convex and model selection type aggregation.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Birgé, L.: Model selection for Gaussian regression with random design. Prépublication n. 783, Laboratoire de Probabilités et Mod‘eles Aléatoires, Universités Paris 6 - Paris 7 (2002)
Birgé, L., Massart, P.: Gaussian model selection. J. Eur. Math. Soc. 3, 203–268 (2001)
Catoni, O.: Statistical Learning Theory and Stochastic Optimization. In: Ecole d’Eté de Probabilités de Saint-Flour 2001. Lecture Notes in Mathematics, Springer, N.Y. (2001) (to appear)
Devroye, L., Györfi, L., Lugosi, G.: A Probabilistic Theory of Pattern Recognition. Springer, N.Y. (1996)
Györfi, L., Kohler, M., Krzyżak, A., Walk, H.: A Distribution-Free Theory of Nonparametric Regression. Springer, N.Y (2002)
Juditsky, A., Nemirovski, A.: Functional aggregation for nonparametric estimation. Annals of Statistics 28, 681–712 (2000)
Nemirovski, A.: Topics in Non-parametric Statistics. In: Ecole d’Eté de Probabilités de Saint-Flour XXVIII - 1998. Lecture Notes in Mathematics, vol. 1738, Springer, N.Y. (2000)
Tsybakov, A.: Introduction à l’estimation non-paramétrique. Springer, Heidelberg (2003) (to appear)
Wegkamp, M.: Model selection in nonparametric regression. Annals of Statistics 31 (2001) (to appear)
Yang, Y.: Combining different procedures for adaptive regression. J. of Multivariate Analysis 74, 135–161 (2000)
Yang, Y.: Aggregating regression procedures for a better performance (2001) (manuscript )
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Tsybakov, A.B. (2003). Optimal Rates of Aggregation. In: Schölkopf, B., Warmuth, M.K. (eds) Learning Theory and Kernel Machines. Lecture Notes in Computer Science(), vol 2777. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-45167-9_23
Download citation
DOI: https://doi.org/10.1007/978-3-540-45167-9_23
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40720-1
Online ISBN: 978-3-540-45167-9
eBook Packages: Springer Book Archive