Robustness analysis of a maximum correntropy framework for linear regression

被引：10
|
作者：
Bako, Laurent [1 ]
机构：
[1] Univ Lyon, Ecole Cent Lyon, Lab Ampere, Lyon, France
来源：
AUTOMATICA | 2018年 / 87卷
关键词：
Robust estimation; System identification; Maximum correntropy; Outliers; CRITERION;
D O I：
10.1016/j.automatica.2017.09.006
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
In this paper we formulate a solution of the robust linear regression problem in a general framework of correntropy maximization. Our formulation yields a unified class of estimators which includes the Gaussian and Laplacian kernel-based correntropy estimators as special cases. An analysis of the robustness properties is then provided. The analysis includes a quantitative characterization of the informativity degree of the regression which is appropriate for studying the stability of the estimator. Using this tool, a sufficient condition is expressed under which the parametric estimation error is shown to be bounded. Explicit expression of the bound is given and discussion on its numerical computation is supplied. For illustration purpose, two special cases are numerically studied. (C) 2017 Elsevier Ltd. All rights reserved.
引用
收藏
页码：218 / 225
页数：8
相关论文
共 50 条
  • [21] Robust regression framework with asymmetrically analogous to correntropy-induced loss
    Yang, Liming
    Ding, Guangsheng
    Yuan, Chao
    Zhang, Min
    [J]. KNOWLEDGE-BASED SYSTEMS, 2020, 191
  • [22] Variational Bayesian-Based Maximum Correntropy Cubature Kalman Filter With Both Adaptivity and Robustness
    He, Jingjing
    Sun, Changku
    Zhang, Baoshang
    Wang, Peng
    [J]. IEEE SENSORS JOURNAL, 2021, 21 (02) : 1982 - 1992
  • [23] Bilinear Model-Based Maximum Likelihood Linear Regression Speaker Adaptation Framework
    Song, Hwa Jeon
    Kim, Hyung Soon
    [J]. IEEE SIGNAL PROCESSING LETTERS, 2009, 16 (12) : 1063 - 1066
  • [24] A NOTE ON ASYMMETRY AND ROBUSTNESS IN LINEAR-REGRESSION
    CARROLL, RJ
    WELSH, AH
    [J]. AMERICAN STATISTICIAN, 1988, 42 (04): : 285 - 287
  • [25] APPLICATION OF MAXIMUM LIKELIHOOD TO NON-LINEAR REGRESSION-ANALYSIS
    QUEDNAU, HD
    [J]. BIOMETRISCHE ZEITSCHRIFT, 1975, 17 (04): : 225 - 231
  • [26] Electricity Consumption Forecasting using Support Vector Regression with the Mixture Maximum Correntropy Criterion
    Duan, Jiandong
    Tian, Xuan
    Ma, Wentao
    Qiu, Xinyu
    Wang, Peng
    An, Lin
    [J]. ENTROPY, 2019, 21 (07)
  • [27] Recursive robust least squares support vector regression based on maximum correntropy criterion
    Chen, Xiaobo
    Yang, Jian
    Liang, Jun
    Ye, Qiaolin
    [J]. NEUROCOMPUTING, 2012, 97 : 63 - 73
  • [28] Maximum Total Improper Complex Correntropy Algorithm for Widely Linear Adaptive Filtering
    Fu, Lianqing
    Zhou, Li
    [J]. IEEE ACCESS, 2022, 10 : 119259 - 119268
  • [29] Common framework for linear regression
    Hoskuldsson, Agnar
    [J]. CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 2015, 146 : 250 - 262
  • [30] Maximum correntropy unscented filter
    Liu, Xi
    Chen, Badong
    Xu, Bin
    Wu, Zongze
    Honeine, Paul
    [J]. INTERNATIONAL JOURNAL OF SYSTEMS SCIENCE, 2017, 48 (08) : 1607 - 1615
12345