Sample Complexity of Classifiers Taking Values in Q, Application to Multi-Class SVMs

被引：8
|
作者：
Guermeur, Yann [1 ]
机构：
[1] LORIA, CNRS, F-54506 Vandoeuvre Les Nancy, France
来源：
COMMUNICATIONS IN STATISTICS-THEORY AND METHODS | 2010年 / 39卷 / 03期
关键词：
Generalized VC dimensions; Multi-class support vector machines; Rademacher complexity; Sample complexity; CLASSIFICATION;
D O I：
10.1080/03610920903140288
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：
Bounds on the risk play a crucial role in statistical learning theory. They usually involve as capacity measure of the model studied the VC dimension or one of its extensions. In classification, such oVC dimensionso exist for models taking values in {0, 1}, [[1, Q]], and . We introduce the generalizations appropriate for the missing case, the one of models with values in Q. This provides us with a new guaranteed risk for M-SVMs. For those models, a sharper bound is obtained by using the Rademacher complexity.
引用
收藏
页码：543 / 557
页数：15
相关论文
共 41 条
  • [31] A divide and conquer approach for imbalanced multi-class classification and its application to medical decision making
    Li, Hu
    PAKISTAN JOURNAL OF PHARMACEUTICAL SCIENCES, 2016, 29 (02) : 743 - 751
  • [32] Determination of sample size for a multi-class classifier based on single-nucleotide polymorphisms: a volume under the surface approach
    Xinyu Liu
    Yupeng Wang
    TN Sriram
    BMC Bioinformatics, 15
  • [33] Determination of sample size for a multi-class classifier based on single-nucleotide polymorphisms: a volume under the surface approach
    Liu, Xinyu
    Wang, Yupeng
    Sriram, T. N.
    BMC BIOINFORMATICS, 2014, 15
  • [34] Multi-class computational evolution: development, benchmark evaluation and application to RNA-Seq biomarker discovery
    Nathaniel M. Crabtree
    Jason H. Moore
    John F. Bowyer
    Nysia I. George
    BioData Mining, 10
  • [35] Cost-Sensitive back-propagation neural networks with binarization techniques in addressing multi-class problems and non-competent classifiers
    Zhang, Zhong-Liang
    Luo, Xing-Gang
    Garcia, Salvador
    Herrera, Francisco
    APPLIED SOFT COMPUTING, 2017, 56 : 357 - 367
  • [36] Multi-class computational evolution: development, benchmark evaluation and application to RNA-Seq biomarker discovery
    Crabtree, Nathaniel M.
    Moore, Jason H.
    Bowyer, John F.
    George, Nysia I.
    BIODATA MINING, 2017, 10
  • [37] An Industrial Application Towards Classification and Optimization of Multi-Class Tile Surface Defects Based on Geometric and Wavelet Features
    Coskun, Huseyin
    Yigit, Tuncay
    Uncu, Ismail Serkan
    Ersoy, Mevlut
    Topal, Ali
    TRAITEMENT DU SIGNAL, 2022, 39 (06) : 2011 - 2022
  • [38] An overview of ensemble methods for binary classifiers in multi-class problems: Experimental study on one-vs-one and one-vs-all schemes
    Galar, Mikel
    Fernandez, Alberto
    Barrenechea, Edurne
    Bustince, Humberto
    Herrera, Francisco
    PATTERN RECOGNITION, 2011, 44 (08) : 1761 - 1776
  • [39] FB Dictionary Based SSBL-EM and Its Application for Multi-Class SSVEP Classification Using Eight-Channel EEG Signals
    Gupta, Vipin
    Pachori, Ram Bilas
    IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2022, 71
  • [40] U-Net feature fusion for multi-class semantic segmentation of urban fabrics from Sentinel-2 imagery: an application on Grand Est Region, France
    Wenger, Romain
    Puissant, Anne
    Weber, Jonathan
    Idoumghar, Lhassane
    Forestier, Germain
    INTERNATIONAL JOURNAL OF REMOTE SENSING, 2022, 43 (06) : 1983 - 2011
12345