Groupwise Retargeted Least-Squares Regression

Groupwise Retargeted Least-Squares Regression
复制标题

DOI:
10.1109/tnnls.2017.2651169
复制
发表时间:
2018-04
影响因子:
10.4
通讯作者:
Lingfeng Wang;Chunhong Pan
Lingfeng Wang;Chunhong Pan
中科院分区:
计算机科学1区
文献类型:
--
作者:
Lingfeng Wang;Chunhong Pan

文献摘要

被引文献

相似文献

在本文中,我们提出了一种新的用于多类别分类的GroupWise重定目标最小二乘回归(GReLSR)模型。GReLSR背后的主要动机是利用额外的正则化来限制ReLSR的翻译值,以便它们在同一类内应该是相似的。通过分析ReLSR的回归目标,我们提出了一种新的ReLSR公式,其中转换值被显式地表示出来。在新公式的基础上,判别最小二乘回归可视为零平移值ReLSR的特例。此外,在ReLSR中加入了GroupWise约束,形成了新的GReLSR模型。在各种机器学习数据集上的大量实验表明,我们的方法比目前最先进的方法性能更好。
In this brief, we propose a new groupwise retargeted least squares regression (GReLSR) model for multicategory classification. The main motivation behind GReLSR is to utilize an additional regularization to restrict the translation values of ReLSR, so that they should be similar within same class. By analyzing the regression targets of ReLSR, we propose a new formulation of ReLSR, where the translation values are expressed explicitly. On the basis of the new formulation, discriminative least-squares regression can be regarded as a special case of ReLSR with zero translation values. Moreover, a groupwise constraint is added to ReLSR to form the new GReLSR model. Extensive experiments on various machine leaning data sets illustrate that our method outperforms the current state-of-the-art approaches.