Abstract
We construct estimators of regression functions and prove theorems on their errors in two different cases. In the first case, we consider the so-called adaptive estimators whose error is close to the optimal one for a whole family of classes of possible regression functions; the adaptivity of the estimators is connectedwith the fact that they are constructedwithout any information about the choice of the class. In the second case, the class of possible regression functions is fixed; however, the marginal measure is unknown and the estimator is constructed without any information about this measure. Its error turns out to be close to the minimal possible (in the worst case) error.
Similar content being viewed by others
References
F. Cucker and S. Smale, “On the mathematical foundations of learning,” Bull. Amer. Math. Soc. (N. S.) 39(1), 1–49 (2002).
R. DeVore, G. Kerkyacharian, D. Picard, and V. Temlyakov, “Approximation methods for supervised learning,” Found. Comput. Math. 6(1), 3–58 (2006).
V. N. Temlyakov, “Approximation in learning theory,” Constr. Approx. 27(1), 33–74 (2008).
S. V. Konyagin and E. D. Livshits, “On adaptive estimators in the statistical theory of learning,” in Trudy Mat. Inst. Steklov Vol. 260: Function Theory and Nonlinear Partial Differential Equations, Collection of papers devoted to the 70th anniversary of Corresponding Member of the Russian Academy of Sciences S. I. Pokhozhaev (Nauka, Moscow, 2008), pp. 193–201 [in Russian]. [Proc. Steklov Inst.Math., Vol. 260, pp. 185–193, 2008, in English].
L. Györfi, M. Kohler, A. Krzyżak, and W. Harro, A Distribution-Free Theory of Nonparametric Regression, in Springer Ser. Statist. (Springer-Verlag, New York, 2002).
S. Mendelson and R. Vershynin, “Entropy and the combinatorial dimension,” Invent. Math. 152(1), 37–55 (2003).
M. Rudelson and R. Vershynin, “Combinatorics of random processes and sections of convex bodies,” Ann. of Math. (2) 164(2), 603–648 (2006).
Author information
Authors and Affiliations
Corresponding author
Additional information
Original Russian Text © Yu. V. Malykhin, 2009, published in Matematicheskie Zametki, 2009, Vol. 86, No. 5, pp. 725–732.
Rights and permissions
About this article
Cite this article
Malykhin, Y.V. Upper bounds for errors of estimators in a problem of nonparametric regression: the adaptive case and the case of unknown measure ρX . Math Notes 86, 682–689 (2009). https://doi.org/10.1134/S0001434609110108
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S0001434609110108