Robust support vector regression with generic quadratic nonconvex ε-insensitive loss

Robust support vector regression with generic quadratic nonconvex ε-insensitive loss
复制标题

具有通用二次非凸 ε 不敏感损失的鲁棒支持向量回归

DOI:
10.1016/j.apm.2020.01.053
复制
发表时间:
2020-06
影响因子:
5
通讯作者:
Xiangyu Hua
Xiangyu Hua
中科院分区:
工程技术2区
文献类型:
--
作者:
Yafen Ye;Junbin Gao;Yuan-Hai Shao;Chunna Li;Yan Jin;Xiangyu Hua

文献摘要

参考文献

被引文献

相似文献

在本文中,我们提出了一种具有新颖的通用非凸二次 ε 不敏感损失函数的鲁棒支持向量回归。该方法对异常值或噪声具有鲁棒性,因为它可以通过调整弹性区间参数和自适应鲁棒参数来自适应控制损失值,减少异常值或噪声对决策函数的负面影响。考虑到优化问题的非凸性质,采用凹凸规划过程来解决所提出的问题。在两个人工数据集和三个真实数据集上的实验结果表明,该方法在鲁棒性和泛化能力上均优于支持向量回归、L1范数支持向量回归、最小二乘支持向量回归、鲁棒最小二乘支持向量回归和带有Huber损失函数的支持向量回归。
In this paper, we propose a robust support vector regression with a novel generic nonconvex quadratic ε-insensitive loss function. The proposed method is robust to outliers or noise since it can adaptively control the loss value and decrease the negative influence of outliers or noise on the decision function by adjusting the elastic interval parameter and adaptive robustification parameter. Given the nature of the nonconvexity of the optimization problem, a concave-convex programming procedure is employed to solve the proposed problem. Experimental results on two artificial data sets and three real-world data sets indicate that the proposed method outperforms support vector regression,L1-norm support vector regression, least squares support vector regression, robust least squares support vector regression, and support vector regression with the Huber loss function on both robustness and generalization ability.
DOI: 10.1016/j.neucom.2015.09.024
发表时间: 2016-01
期刊: Neurocomputing
影响因子: 6
作者:
M. Tanveer;Mohit Mangal;I. Ahmad;Y. Shao
通讯作者: M. Tanveer;Mohit Mangal;I. Ahmad;Y. Shao
斜坡损失非并行支持向量回归:稳健、稀疏且可扩展的近似
DOI: 10.1016/j.knosys.2018.02.016
发表时间: 2018-05
影响因子: 8.8
作者:
Tang Long;Tian Yingjie;Yang Chunyan;Pardalos Panos M.
通讯作者: Pardalos Panos M.
DOI: 10.1080/01621459.2019.1660170
发表时间: 2020
影响因子: 3.7
作者:
Sun R;Lin X
通讯作者: Lin X
用于异常值回归的鲁棒非凸最小二乘损失函数
DOI: 10.1016/j.knosys.2014.08.003
发表时间: 2014-11
期刊: Knowledge-Based System
影响因子: --
作者:
Wang Kuaini;Zhong Ping
通讯作者: Zhong Ping
DOI: --
发表时间: 1996-12
期刊: --
影响因子: --
作者:
H. Drucker;C. Burges;L. Kaufman;Alex Smola;V. Vapnik
通讯作者: H. Drucker;C. Burges;L. Kaufman;Alex Smola;V. Vapnik