Leave-one-out bounds for support vector regression model selection

被引：79
|
作者：
Chang, MW [1 ]
Lin, CJ [1 ]
机构：
[1] Natl Taiwan Univ, Dept Comp Sci & Informat Engn, Taipei 106, Taiwan
来源：
NEURAL COMPUTATION | 2005年 / 17卷 / 05期
关键词：
D O I：
10.1162/0899766053491869
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Minimizing bounds of leave-one-out errors is an important and efficient approach for support vector machine (SVM) model selection. Past research focuses on their use for classification but not regression. In this letter, we derive various leave-one-out bounds for support vector regression (SVR) and discuss the difference from those for classification. Experiments demonstrate that the proposed bounds are competitive with Bayesian SVR for parameter selection. We also discuss the differentiability of leave-one-out bounds.
引用
收藏
页码：1188 / 1222
页数：35
相关论文
共 50 条
  • [11] Fast leave-one-out methods for inference, model selection, and diagnostic checking
    Belotti, Federico
    Peracchi, Franco
    STATA JOURNAL, 2020, 20 (04): : 785 - 804
  • [12] Approximate Leave-One-Out Cross Validation for Regression With Regularizers
    Auddy, Arnab
    Zou, Haolin
    Rad, Kamiar Rahnama
    Maleki, Arian
    IEEE Transactions on Information Theory, 2024, 70 (11) : 8040 - 8071
  • [13] Limitations of Bayesian Leave-One-Out Cross-Validation for Model Selection
    Gronau Q.F.
    Wagenmakers E.-J.
    Computational Brain & Behavior, 2019, 2 (1) : 1 - 11
  • [14] The leave-one-out kernel
    Tsuda, K
    Kawanabe, M
    ARTIFICIAL NEURAL NETWORKS - ICANN 2002, 2002, 2415 : 727 - 732
  • [15] Lower bounds for training and leave-one-out estimates of the generalization error
    Gavin, G
    Teytaud, O
    ARTIFICIAL NEURAL NETWORKS - ICANN 2002, 2002, 2415 : 583 - 588
  • [16] Leave-one-out cross-validation-based model selection for multi-input multi-output support vector machine
    Mao, Wentao
    Mu, Xiaoxia
    Zheng, Yanbin
    Yan, Guirong
    NEURAL COMPUTING & APPLICATIONS, 2014, 24 (02): : 441 - 451
  • [17] Leave-one-out cross-validation-based model selection for multi-input multi-output support vector machine
    Wentao Mao
    Xiaoxia Mu
    Yanbin Zheng
    Guirong Yan
    Neural Computing and Applications, 2014, 24 : 441 - 451
  • [18] Leave-one-out Unfairness
    Black, Emily
    Fredrikson, Matt
    PROCEEDINGS OF THE 2021 ACM CONFERENCE ON FAIRNESS, ACCOUNTABILITY, AND TRANSPARENCY, FACCT 2021, 2021, : 285 - 295
  • [19] Fast leave-one-out evaluation for dynamic gene selection
    Yhao, Y
    Kwoh, CK
    SOFT COMPUTING, 2006, 10 (04) : 346 - 350
  • [20] An efficient method for computing leave-one-out error in support vector machines with Gaussian kernels
    Lee, MMS
    Keerthi, SS
    Ong, CJ
    DeCoste, D
    IEEE TRANSACTIONS ON NEURAL NETWORKS, 2004, 15 (03): : 750 - 757
12345