LEAST SQUARE REGRESSION WITH COEFFICIENT REGULARIZATION BY GRADIENT DESCENT-Reference-Cited by-同舟云学术

LEAST SQUARE REGRESSION WITH COEFFICIENT REGULARIZATION BY GRADIENT DESCENT

Published:2012-01 Issue:01 Volume:10 Page:1250005
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:

HUANG JUAN¹²,CHEN HONG³,LI LUOQING¹

Affiliation:

1. Faculty of Mathematics and Computer Science, Hubei University, Wuhan 430062, P. R. China

2. School of Mathematics and Physics, China University of Geosciences, Wuhan 430074, P. R. China

3. College of Science, Huazhong Agricultural University, Wuhan 430070, P. R. China

Abstract

We propose a stochastic gradient descent algorithm for the least square regression with coefficient regularization. An explicit expression of the solution via sampling operator and empirical integral operator is derived. Learning rates are given in terms of the suitable choices of the step sizes and regularization parameters.

Publisher

World Scientific Pub Co Pte Lt

Subject

Applied Mathematics,Information Systems,Signal Processing

Link

https://www.worldscientific.com/doi/pdf/10.1142/S021969131100447X

Reference21 articles.

1. Theory of reproducing kernels

2. Sparsity and incoherence in compressive sampling

3. Model Selection for Regularized Least-Squares Algorithm in Learning Theory

4. Learning rates of gradient descent algorithm for classification

Cited by 5 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. Learning rates for multi-task regularization networks;Neurocomputing;2021-11

2. Addressing the illumination challenge in two‐dimensional face recognition: a survey;IET Computer Vision;2015-12

3. CONVERGENCE ANALYSIS OF COEFFICIENT-BASED REGULARIZATION UNDER MOMENT INCREMENTAL CONDITION;International Journal of Wavelets, Multiresolution and Information Processing;2013-12

4. ELASTIC-NET REGULARIZATION FOR LOW-RANK MATRIX RECOVERY;International Journal of Wavelets, Multiresolution and Information Processing;2012-09

5. THE COEFFICIENT REGULARIZED REGRESSION WITH RANDOM PROJECTION;International Journal of Wavelets, Multiresolution and Information Processing;2012-03