CONVERGENCE ANALYSIS OF COEFFICIENT-BASED REGULARIZATION UNDER MOMENT INCREMENTAL CONDITION-Reference-Cited by-同舟云学术

CONVERGENCE ANALYSIS OF COEFFICIENT-BASED REGULARIZATION UNDER MOMENT INCREMENTAL CONDITION

Published:2013-12 Issue:01 Volume:12 Page:1450008
ISSN:0219-6913
Container-title:International Journal of Wavelets, Multiresolution and Information Processing
language:en
Short-container-title:Int. J. Wavelets Multiresolut Inf. Process.

Author:

WANG CHENG¹,CAI JIA²

Affiliation:

1. Department of Mathematics, Huizhou University, Huizhou, Guangdong 516007, P. R. China

2. School of Mathematics and Statistics, Guangdong University of Finance and Economics, Guangzhou, Guangdong 510320, P. R. China

Abstract

In this paper, we investigate coefficient-based regularized least squares regression problem in a data dependent hypothesis space. The learning algorithm is implemented with samples drawn by unbounded sampling processes and the error analysis is performed by a stepping-stone technique. A new error decomposition technique is proposed for the error analysis. The regularization parameters in our setting provide much more flexibility and adaptivity. Sharp learning rates are addressed by means of l2-empirical covering numbers under a moment hypothesis condition.

Publisher

World Scientific Pub Co Pte Lt

Subject

Applied Mathematics,Information Systems,Signal Processing

Link

https://www.worldscientific.com/doi/pdf/10.1142/S0219691314500088

Reference20 articles.

1. Theory of reproducing kernels

2. Probability Inequalities for the Sum of Independent Random Variables

3. Learning Theory

4. Unified approach to coefficient-based regularized regression

Cited by 6 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Reproducing property of bounded linear operators and kernel regularized least square regressions;International Journal of Wavelets, Multiresolution and Information Processing;2024-04-22

2. Learning rates for the kernel regularized regression with a differentiable strongly convex loss;Communications on Pure & Applied Analysis;2020

3. Support vector machines regression with unbounded sampling;Applicable Analysis;2018-02-08

4. Statistical consistency of coefficient-based conditional quantile regression;Journal of Multivariate Analysis;2016-07

5. Constructive analysis for coefficient regularization regression algorithms;Journal of Mathematical Analysis and Applications;2015-11