Apportioned margin approach for cost sensitive large margin classifiers

被引:0
|
作者
Lee-Ad Gottlieb
Eran Kaufman
Aryeh Kontorovich
机构
[1] Ariel University,
[2] Ben-Gurion University,undefined
来源
Annals of Mathematics and Artificial Intelligence | 2021年 / 89卷
关键词
Multi-class classification; Asymmetric cost; Linear classifiers; 68Q32;
D O I
暂无
中图分类号
学科分类号
摘要
We consider the problem of cost sensitive multiclass classification, where we would like to increase the sensitivity of an important class at the expense of a less important one. We adopt an apportioned margin framework to address this problem, which enables an efficient margin shift between classes that share the same boundary. The decision boundary between all pairs of classes divides the margin between them in accordance with a given prioritization vector, which yields a tighter error bound for the important classes while also reducing the overall out-of-sample error. In addition to demonstrating an efficient implementation of our framework, we derive generalization bounds, demonstrate Fisher consistency, adapt the framework to Mercer’s kernel and to neural networks, and report promising empirical results on all accounts.
引用
收藏
页码:1215 / 1235
页数:20
相关论文
共 50 条
  • [1] Apportioned margin approach for cost sensitive large margin classifiers
    Gottlieb, Lee-Ad
    Kaufman, Eran
    Kontorovich, Aryeh
    ANNALS OF MATHEMATICS AND ARTIFICIAL INTELLIGENCE, 2021, 89 (12) : 1215 - 1235
  • [2] Incremental margin algorithm for large margin classifiers
    Leite, Saul C.
    Neto, Raul Fonseca
    NEUROCOMPUTING, 2008, 71 (7-9) : 1550 - 1560
  • [3] Adaptively Weighted Large Margin Classifiers
    Wu, Yichao
    Liu, Yufeng
    JOURNAL OF COMPUTATIONAL AND GRAPHICAL STATISTICS, 2013, 22 (02) : 416 - 432
  • [4] Convex Bidirectional Large Margin Classifiers
    Qi, Zhengling
    Liu, Yufeng
    TECHNOMETRICS, 2019, 61 (02) : 176 - 186
  • [5] Multiplicative updates for large margin classifiers
    Sha, F
    Saul, LK
    Lee, DD
    LEARNING THEORY AND KERNEL MACHINES, 2003, 2777 : 188 - 202
  • [6] Large margin nearest neighbor classifiers
    Domeniconi, C
    Gunopulos, D
    Peng, J
    IEEE TRANSACTIONS ON NEURAL NETWORKS, 2005, 16 (04): : 899 - 909
  • [7] An approach to large margin design of prototype-based pattern classifiers
    He, Tingting
    Hu, Yu
    Huo, Qiang
    2007 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL II, PTS 1-3, 2007, : 625 - +
  • [8] Large margin classifiers based on affine hulls
    Cevikalp, Hakan
    Triggs, Bill
    Yavuz, Hasan Serhan
    Kucuk, Yalcin
    Kucuk, Mahide
    Barkana, Atalay
    NEUROCOMPUTING, 2010, 73 (16-18) : 3160 - 3168
  • [9] Face detection using large margin classifiers
    Yang, MH
    Roth, D
    Ahuja, N
    2001 INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOL II, PROCEEDINGS, 2001, : 665 - 668
  • [10] Probability estimation for large-margin classifiers
    Wang, Junhui
    Shen, Xiaotong
    Liu, Yufeng
    BIOMETRIKA, 2008, 95 (01) : 149 - 167