Abstract
In this paper high order Parzen windows stated by means of basic window functions are studied for understanding some algorithms in learning theory and randomized sampling in multivariate approximation. Learning rates are derived for the least-square regression and density estimation on bounded domains under some decay conditions on the marginal distributions near the boundary. These rates can be almost optimal when the marginal distributions decay fast and the order of the Parzen windows is large enough. For randomized sampling in shift-invariant spaces, we consider the situation when the sampling points are neither i.i.d. nor regular, but are noised from regular grids by probability density functions. The approximation orders are estimated by means of the regularity of the approximated function and the density function and the order of the Parzen windows.
Similar content being viewed by others
References
Aldroubi, A., Gröchenig, K.: Non-uniform sampling and reconstruction in shift-invariant spaces. SIAM Rev. 43, 585–620 (2001)
Bartlett, M.S.: Statistical estimation of density functions. Sankhya Ser. A 25, 245–254 (1963)
Belkin, M., Niyogi, P.: Laplacian eigenmaps for dimensionality reduction and data representation. Neural Comput. 15, 1373–1396 (2003)
de Boor, C.: A Practical Guide to Splines, Applied Mathematical Sciences, vol. 27. Springer, New York (1978)
Caponnetto, A., Smale, S.: Risk bounds for random regression graphs. Found. Comput. Math. 7, 495–528 (2007)
Daubechies, I.: Ten Lectures on Wavelets. SIAM, Philadelphia (1992)
De Vito, E., Caponnetto, A., Rosasco, L.: Model selection for regularized least-squares algorithm in learning theory. Found. Comput. Math. 5, 59–85 (2005)
Devroye, L., Lugosi, G.: Combinatorial Methods in Density Estimation. Springer, Heidelberg (2000)
Evgeniou, T., Pontil, M., Poggio, T.: Regularization networks and suport vector machines. Adv. Comput. Math. 13, 1–50 (2000)
Fukunaga, K.: Introduction to Statistical Pattern Recognition. Academic, London (1990)
Hardin, D., Tsamardinos, I., Aliferis, C.F.: A theoretical characterization of linear SVM-based feature selection. In: Proc. of the 21st International Conference on Machine Learning, Banff, 4–8 July 2004
Jia, R.Q.: Approximation with scaled shift-invariant spaces by means of quasi-projection operators. J. Approx. Theory 131, 30–46 (2004)
Lei, J.J., Jia, R.Q., Cheney, E.W.: Approximation from shift-invariant spaces by integral operators. SIAM J. Math. Anal. 28, 481–498 (1997)
Marron, J.S., Wand, M.P.: Exact mean integrated square error. Ann. Statist. 20, 712–736 (1992)
Mukherjee, S., Zhou, D.X.: Learning coordinate covariances via gradients. J. Mach. Learn. Res. 7, 519–549 (2006)
Parzen, E.: On the estimation of a probability density function and the mode. Ann. Math. Stat. 33, 1049–1051 (1962)
Pinelis, I.: Optimum bounds for the distributions of martingales in Banach spaces. Ann. Probab. 22, 1679–1706 (1994)
Smale, S., Zhou, D.X.: Shannon sampling and function reconstruction from point values. Bull. Amer. Math. Soc. 41, 279–305 (2004)
Smale, S., Zhou, D.X., Shannon sampling II. Connections to learning theory. Appl. Comput. Harmon. Anal. 19, 285–302 (2005)
Smale, S., Zhou, D.X.: Learning theory estimates via integral operators and their approximations. Constr. Approx. 26, 153–172 (2007)
Smale, S., Zhou, D.X.: Online learning with Markov sampling. Anal. Appl. (to appear)
Stone, C.J.: Optimal rates of convergence for nonparametric estimators. Ann. Stat. 8, 1348–1360 (1980)
Strang, G., Fix, G.: A Fourier analysis of the finite-element variational method. In: Geymonat, G. (ed.) Constructive Aspects of Functional Analysis, C. I. M. E., pp. 793–840 (1973)
Vapnik, V.: Statistical Learning Theory. Wiley, New York (1998)
Wand, M.P., Jones, M.C.: Kernel Smoothing, Monographs on Statistics and Applied Probability, vol. 60. Chapman & Hall, London (1995)
Wu, Q., Ying, Y., Zhou, D.X.: Learning rates of least-square regularized regression. Found. Comput. Math. 6, 171–192 (2006)
Ye, G.B., Zhou, D.X.: Learning and approximation by Gaussians on Riemannian manifolds. Adv. Comput. Math. doi:10.1007/s10444-007-9049-0
Ying, Y., Zhou, D.X.: Learnability of Gaussians with flexible variances. J. Mach. Learn. Res. 8, 249–276 (2007)
Author information
Authors and Affiliations
Corresponding author
Additional information
Communicated by Juan Manuel Peña.
Supported partially by City University of Hong Kong [Project No. 7002126], National Science Fund for Distinguished Young Scholars of China [Project No. 10529101], and National Basic Research Program of China [Project No. 973-2006CB303102].
Rights and permissions
About this article
Cite this article
Zhou, XJ., Zhou, DX. High order Parzen windows and randomized sampling. Adv Comput Math 31, 349 (2009). https://doi.org/10.1007/s10444-008-9073-8
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s10444-008-9073-8