Analysis of approximation by linear operators on variable \(L_\rho^{p(\cdot)}\) spaces and applications in learning theory. (English) Zbl 1470.41021

Summary: This paper is concerned with approximation on variable \(L_\rho^{p(\cdot)}\) spaces associated with a general exponent function \(p\) and a general bounded Borel measure \(\rho\) on an open subset \(\Omega\) of \(\mathbb{R}^d\). We mainly consider approximation by Bernstein type linear operators. Under an assumption of log-Hölder continuity of the exponent function \(p\), we verify a conjecture raised previously about the uniform boundedness of Bernstein-Durrmeyer and Bernstein-Kantorovich operators on the \(L_\rho^{p(\cdot)}\) space. Quantitative estimates for the approximation are provided for high orders of approximation by linear combinations of such positive linear operators. Motivating connections to classification and quantile regression problems in learning theory are also described.


41A36 Approximation by positive operators
Full Text: DOI


[1] Bernstein, S. N., Démonstration du téoréme de Weirerstrass, fondée sur le calcul des probabilités, Communications of the Kharkov Mathematical Society, 13, 1-2 (1913)
[2] Kantorovich, L. V., Sur certaines developments suivant les polynômes de la forme de S. Bernstein I-II, Comptes Rendus de l’Académie des Sciences de L’URSS A, 563-568, 595-600 (1930) · JFM 57.1393.02
[3] Durrmeyer, J. L., Une formule d’inversion de la transformée Laplace: applications á la théorie des moments [Thése de 3e cycle: Sciences] (1967), Paris, France: Faculté des Sciences, l’Université Paris, Paris, France
[4] Berens, H.; Lorentz, G. G., Inverse theorems for Bernstein polynomials, Indiana University Mathematics Journal, 21, 693-708 (1972) · Zbl 0262.41006
[5] Berens, H.; DeVore, R. A., Quantitative Korovkin theorems for positive linear operators on \(L P\)-spaces, Transactions of the American Mathematical Society, 245, 349-361 (1978) · Zbl 0397.41010
[6] Ditzian, Z.; Totik, V., Moduli of Smoothness. Moduli of Smoothness, Springer Series in Computational Mathematics, 9 (1987), New York, NY, USA: Springer, New York, NY, USA · Zbl 0666.41001
[7] Diening, L.; Harjulehto, P.; Hästö, P.; Ruzicka, M., Lebesgue and Sobolev Spaces with Variable Exponents (2011), Berlin, Germany: Springer, Berlin, Germany · Zbl 1222.46002
[8] Orlicz, W., Über konjugierte Exponentenfolgen, Studia Mathematica, 3, 200-211 (1931) · JFM 57.0251.02
[9] Acerbi, E.; Mingione, G., Regularity results for a class of functionals with non-standard growth, Archive for Rational Mechanics and Analysis, 156, 2, 121-140 (2001) · Zbl 0984.49020
[10] Kovácik, O.; Rákosnk, J., On spaces \(L^{p \left(x\right)}\) and \(W^{1, p \left(x\right)}\), Czechoslovak Mathematical Journal, 41, 116, 592-618 (1991)
[11] Zhou, D. X., Approximation by positive linear operators on variables \(L^{p(x)}\) spaces, Journal of Applied Functional Analysis, 9, 3-4, 379-391 (2014) · Zbl 1358.41020
[12] Zhou, D. X.; Jetter, K., Approximation with polynomial kernels and {SVM} classifiers, Advances in Computational Mathematics, 25, 1-3, 323-344 (2006) · Zbl 1095.68103
[13] Berdysheva, E. E.; Jetter, K., Multivariate Bernstein-Durrmeyer operators with arbitrary weight functions, Journal of Approximation Theory, 162, 3, 576-598 (2010) · Zbl 1195.41024
[14] Tsybakov, A. B., Optimal aggregation of classifiers in statistical learning, The Annals of Statistics, 32, 1, 135-166 (2004) · Zbl 1105.62353
[15] Smale, S.; Zhou, D. X., Learning theory estimates via integral operators and their approximations, Constructive Approximation, 26, 2, 153-172 (2007) · Zbl 1127.68088
[16] Smale, S.; Zhou, D. X., Shannon sampling and function reconstruction from point values, The American Mathematical Society: Bulletin, 41, 3, 279-305 (2004) · Zbl 1107.94007
[17] Hu, T.; Fan, J.; Wu, Q.; Zhou, D. X., Regularization schemes for minimum error entropy principle, Analysis and Applications (2014) · Zbl 1329.68216
[18] Steinwart, I.; Christmann, A., Estimating conditional quantiles with the help of the pinball loss, Bernoulli, 17, 1, 211-225 (2011) · Zbl 1284.62235
[19] Xiang, D. H., A new comparison theorem on conditional quantiles, Applied Mathematics Letters, 25, 1, 58-62 (2012) · Zbl 1358.62043
[20] Lei, J.; Jia, R.; Cheney, E. W., Approximation from shift-invariant spaces by integral operators, SIAM Journal on Mathematical Analysis, 28, 2, 481-498 (1997) · Zbl 0871.41013
[21] Jetter, K.; Zhou, D. X., Order of linear approximation from shift-invariant spaces, Constructive Approximation, 11, 4, 423-438 (1995) · Zbl 0840.41025
[22] Derriennic, M., On multivariate approximation by Bernstein-type polynomials, Journal of Approximation Theory, 45, 2, 155-166 (1985) · Zbl 0578.41010
[23] Berens, H.; Xu, Y.; Chui, C. K., On Bernstein-Durrmeyer polynomials with Jacobi weights, Approximation Theory and Functional Analysis, 25-46 (1991), Boston, Mass, USA: Academic Press, Boston, Mass, USA · Zbl 0715.41013
[24] Li, B.-Z., Approximation by multivariate Bernstein-Durrmeyer operators and learning rates of least-squares regularized regression with multivariate polynomial kernels, Journal of Approximation Theory, 173, 33-55 (2013) · Zbl 1282.41009
[25] Berdysheva, E. E., Uniform convergence of Bernstein-Durrmeyer operators with respect to arbitrary measure, Journal of Mathematical Analysis and Applications, 394, 1, 324-336 (2012) · Zbl 1247.41014
[26] Berdysheva, E. E., Bernstein-Durrmeyer operators with respect to arbitrary measure, II: pointwise convergence, Journal of Mathematical Analysis and Applications, 418, 2, 734-752 (2014) · Zbl 1304.41016
[27] Zhou, D. X., Converse theorems for multidimensional Kantorovich operators, Analysis Mathematica, 19, 1, 85-100 (1993) · Zbl 0808.41012
[28] de Boor, C.; DeVore, R. A.; Ron, A., Approximation from shift-invariant subspaces of \(L_2(R^d)\), Transactions of the American Mathematical Society, 341, 2, 787-806 (1994) · Zbl 0790.41012
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.