Variable Selection for Kernel Classification

被引:0
|
作者
Steel, S. J. [1 ]
Louw, N. [1 ]
Bierman, S. [1 ]
机构
[1] Univ Stellenbosch, Dept Stat & Actuarial Sci, ZA-7602 Matieland, South Africa
关键词
Kernel Fisher discriminant analysis; Support vector machines; Surrogate selection; Wide data sets; COLON-CANCER PREDICTION; REGRESSION;
D O I
10.1080/03610918.2010.534226
中图分类号
O21 [概率论与数理统计]; C8 [统计学];
学科分类号
020208 ; 070103 ; 0714 ;
摘要
In this article, a variable selection procedure, called surrogate selection, is proposed which can be applied when a support vector machine or kernel Fisher discriminant analysis is used in a binary classification problem. Surrogate selection applies the lasso after substituting the kernel discriminant scores for the binary group labels, as well as values for the input variable observations. Empirical results are reported, showing that surrogate selection performs well.
引用
收藏
页码:241 / 258
页数:18
相关论文
共 50 条
  • [1] Supervised classification with variable kernel estimators
    Comon, P
    Cheneval, Y
    [J]. FROM NATURAL TO ARTIFICIAL NEURAL COMPUTATION, 1995, 930 : 1099 - 1106
  • [2] Metric Selection for GPU Kernel Classification
    Shekofteh, S-Kazem
    Noori, Hamid
    Naghibzadeh, Mahmoud
    Yazdi, Hadi Sadoghi
    Froening, Holger
    [J]. ACM TRANSACTIONS ON ARCHITECTURE AND CODE OPTIMIZATION, 2019, 15 (04)
  • [3] Variable Selection for Clustering and Classification
    Jeffrey L. Andrews
    Paul D. McNicholas
    [J]. Journal of Classification, 2014, 31 : 136 - 153
  • [4] Variable Selection for Clustering and Classification
    Andrews, Jeffrey L.
    McNicholas, Paul D.
    [J]. JOURNAL OF CLASSIFICATION, 2014, 31 (02) : 136 - 153
  • [5] Bayesian Approximate Kernel Regression With Variable Selection
    Crawford, Lorin
    Wood, Kris C.
    Zhou, Xiang
    Mukherjee, Sayan
    [J]. JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 2018, 113 (524) : 1710 - 1721
  • [6] Bandwidth Selection for Kernel-Based Classification
    Lindenbaum, Ofir
    Yeredor, Arie
    Averbuch, Amir
    [J]. 2016 IEEE INTERNATIONAL CONFERENCE ON THE SCIENCE OF ELECTRICAL ENGINEERING (ICSEE), 2016,
  • [7] Variable Selection in Kernel Regression Using Measurement Error Selection Likelihoods
    White, Kyle R.
    Stefanski, Leonard A.
    Wu, Yichao
    [J]. JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 2017, 112 (520) : 1587 - 1597
  • [8] EFFICIENT KERNEL-BASED VARIABLE SELECTION WITH SPARSISTENCY
    He, Xin
    Wang, Junhui
    Lv, Shaogao
    [J]. STATISTICA SINICA, 2021, 31 (04) : 2123 - 2151
  • [9] Kernel variable selection for multicategory support vector machines
    Park, Beomjin
    Park, Changyi
    [J]. JOURNAL OF MULTIVARIATE ANALYSIS, 2021, 186
  • [10] Kernel Canonical Discriminant Analysis Based on Variable Selection
    Ikeda, Seiichi
    Sato, Yoshiharu
    [J]. JOURNAL OF ADVANCED COMPUTATIONAL INTELLIGENCE AND INTELLIGENT INFORMATICS, 2009, 13 (04) : 416 - 420