Statistical analysis of the moving least-squares method with unbounded sampling

Moving least-squares method is investigated with samples drawn from unbounded sampling processes. Convergence analysis is established by imposing incremental conditions on moments of sample output and window width. Satisfied convergence rates are derived by means of projection operator and some concentration inequalities.

[1]  Don R. Hush,et al.  Optimal Rates for Regularized Least Squares Regression , 2009, COLT.

[2]  D. H. McLain,et al.  Drawing Contours from Arbitrary Data Points , 1974, Comput. J..

[3]  Ding-Xuan Zhou,et al.  Concentration estimates for learning with unbounded sampling , 2013, Adv. Comput. Math..

[4]  Lorenzo Rosasco,et al.  Elastic-net regularization in learning theory , 2008, J. Complex..

[5]  Luoqing Li,et al.  Learning rates of multi-kernel regularized regression , 2010 .

[6]  Lean Yu,et al.  An evolutionary programming based asymmetric weighted least squares support vector machine ensemble learning methodology for software repository mining , 2012, Inf. Sci..

[7]  Xinge You,et al.  Generalization performance of magnitude-preserving semi-supervised ranking with graph-based regularization , 2013, Inf. Sci..

[8]  Yiming Ying,et al.  Support Vector Machine Soft Margin Classifiers: Error Analysis , 2004, J. Mach. Learn. Res..

[9]  Hong-Yan Wang,et al.  Concentration estimates for the moving least-square method in learning theory , 2011, J. Approx. Theory.

[10]  Jianqing Fan,et al.  Local polynomial modelling and its applications , 1994 .

[11]  Jean-Yves Audibert,et al.  Robust linear least squares regression , 2010, 1010.0074.

[12]  Felipe Cucker,et al.  Learning Theory: An Approximation Theory Viewpoint (Cambridge Monographs on Applied & Computational Mathematics) , 2007 .

[13]  Cheng Wang,et al.  Optimal learning rates for least squares regularized regression with unbounded sampling , 2011, J. Complex..

[14]  H. Wendland.  Local polynomial reproduction and moving least squares approximation , 2001 .

[15]  D. Levin,et al.  Hermite type moving-least-squares approximations , 2006, Comput. Math. Appl..

[16]  Ding-Xuan Zhou,et al.  High order Parzen windows and randomized sampling , 2009, Adv. Comput. Math..

[17]  Jun Fan,et al.  Learning theory approach to minimum error entropy criterion , 2012, J. Mach. Learn. Res..

[18]  Ding-Xuan Zhou,et al.  The covering number in learning theory , 2002, J. Complex..

[19]  G. Fasshauer.  Toward approximate moving least squares approximation with irregularly spaced centers , 2004 .

[20]  Ding-Xuan Zhou,et al.  Learning Theory: An Approximation Theory Viewpoint , 2007 .

[21]  Milan Hladík,et al.  On the possibilistic approach to linear regression models involving uncertain, indeterminate or interval data , 2013, Inf. Sci..

[22]  Dao-Hong Xiang,et al.  Moving least-square method in learning theory , 2010, J. Approx. Theory.

[23]  Yiming Ying,et al.  Learning Rates of Least-Square Regularized Regression , 2006, Found. Comput. Math..

[24]  A. Caponnetto,et al.  Optimal Rates for the Regularized Least-Squares Algorithm , 2007, Found. Comput. Math..

[25]  Yaron Lipman.  Stable Moving Least-Squares , 2009, J. Approx. Theory.

[26]  Yiming Ying,et al.  Multi-kernel regularized classifiers , 2007, J. Complex..

[27]  Ding-Xuan Zhou,et al.  Capacity of reproducing kernel spaces in learning theory , 2003, IEEE Transactions on Information Theory.

[28]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .