A robust classification framework with mixture correntropy

A robust classification framework with mixture correntropy
复制标题

具有混合熵的鲁棒分类框架

DOI:
10.1016/j.ins.2019.04.016
复制
发表时间:
2019-07
影响因子:
8.1
通讯作者:
Qiangqiang Ren
Qiangqiang Ren
中科院分区:
计算机科学1区
文献类型:
--
作者:
Yidan Wang;Liming Yang;Qiangqiang Ren

文献摘要

参考文献

被引文献

相似文献

本文定义了两个不同核函数组合的混合一致熵准则。利用这一非均匀混合相关熵,我们推导出了一个更一般的非凸鲁棒损失函数。提出的混合相关熵也是一种局部相似性度量,不仅改善了相关熵在单一核函数下的局限性,而且能够更加灵活、稳定地处理异质数据。诱导损失融合了最先进的稳健损失函数的优势,更有效。从稳健估计的角度验证了诱导损失的Fisher相合性,并分析了其稳健性。针对这种损失,我们提出了一种稳健的支持向量机框架,并采用半二次优化算法来处理这种非凸性,进一步提高了收敛速度。此外,我们还生成了不同结构的人工数据集,并在基准数据集上施加了不同程度的标签噪声。在这两种类型的数据集上的实现表明,所提出的框架具有优越的灵活性和有效性
In this paper, we define a mixture correntropy criterion where two different kernel functions are combined. We induce a more general nonconvex robust loss function by this heterogenous mixture correntropy. The proposed mixture correntropy is also a local similarity measure that not only improves the limitations of correntropy under a single kernel, but also handles heterogeneous data more flexibly and stably. The induced loss amalgamates the superiors of the state-of-the-art robust loss functions and is more effective. What’s more, we verify the Fisher consistency of the induced loss and analyze the robustness from the view point of robust estimation. With this induced loss, we propose a robust support vector machine (SVM) framework and adopt half quadratic optimization algorithm to handle the nonconvexity and further improve convergent rate. Furthermore, we generate heterogenous structured artificial datasets and impose different levels of label noise on benchmark datasets. Implements on these two types of datasets show the superior flexibility and effectiveness of the proposed framework
DOI: 10.1007/978-1-4899-7687-1_810
发表时间: 2017
期刊: --
影响因子: --
作者:
Xinhua Zhang
通讯作者: Xinhua Zhang
DOI: 10.1201/9781003139041-11
发表时间: 2021-03
期刊: An Introduction to IoT Analytics
影响因子: --
作者:
Harry G. Perros
通讯作者: Harry G. Perros
DOI: 10.1109/ijcnn.2010.5596485
发表时间: 2010-07
期刊: The 2010 International Joint Conference on Neural Networks (IJCNN)
影响因子: --
作者:
Abhishek Singh;J. Príncipe
通讯作者: Abhishek Singh;J. Príncipe
DOI: 10.1007/978-1-4471-5571-3_16
发表时间: 2014
期刊: Fuel
影响因子: 7.4
作者:
Ke-Lin Du;M. Swamy
通讯作者: Ke-Lin Du;M. Swamy
DOI: 10.1016/j.spl.2004.03.002
发表时间: 2004-06-01
影响因子: 0.8
作者:
Lin, Y
通讯作者: Lin, Y