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
  • [21] Feasible adaptation criteria for hybrid wavelet -: Large margin classifiers
    Neumann, J
    Schnörr, C
    Steidl, G
    COMPUTER ANALYSIS OF IMAGES AND PATTERNS, PROCEEDINGS, 2003, 2756 : 588 - 595
  • [22] VC theory of large margin multi-category classifiers
    Guermeur, Yann
    JOURNAL OF MACHINE LEARNING RESEARCH, 2007, 8 : 2551 - 2594
  • [23] Large margin classifiers to generate synthetic data for imbalanced datasets
    Ladeira Marques, Marcelo
    Moraes Villela, Saulo
    Hasenclever Borges, Carlos Cristiano
    APPLIED INTELLIGENCE, 2020, 50 (11) : 3678 - 3694
  • [24] From hyperplanes to large margin classifiers: Applications to SAR ATR
    Zhao, Q
    Principe, JC
    Xu, DX
    AUTOMATIC TARGET RECOGNITION IX, 1999, 3718 : 101 - 109
  • [25] A comparative study of the use of large margin classifiers on seismic data
    Drosou, Krystallenia
    Artemiou, Andreas
    Koukouvinos, Christos
    JOURNAL OF APPLIED STATISTICS, 2015, 42 (01) : 180 - 201
  • [26] Large margin classifiers to generate synthetic data for imbalanced datasets
    Marcelo Ladeira Marques
    Saulo Moraes Villela
    Carlos Cristiano Hasenclever Borges
    Applied Intelligence, 2020, 50 : 3678 - 3694
  • [27] Average Margin Regularization for Classifiers
    Olfat, Matt
    Aswani, Anil
    2020 59TH IEEE CONFERENCE ON DECISION AND CONTROL (CDC), 2020, : 3194 - 3199
  • [28] Cost-sensitive large margin distribution machine for fault detection of wind turbines
    Tang, Mingzhu
    Ding, Steven X.
    Yang, Chunhua
    Cheng, Fanyong
    Shardt, Yuri A. W.
    Long, Wen
    Liu, Daifei
    CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS, 2019, 22 (Suppl 3): : S7525 - S7537
  • [29] Cost-sensitive large margin distribution machine for fault detection of wind turbines
    Mingzhu Tang
    Steven X. Ding
    Chunhua Yang
    Fanyong Cheng
    Yuri A. W. Shardt
    Wen Long
    Daifei Liu
    Cluster Computing, 2019, 22 : 7525 - 7537
  • [30] Maximum margin classifiers with noisy data: A robust optimization approach
    Trafalis, TB
    Gilbert, RC
    PROCEEDINGS OF THE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), VOLS 1-5, 2005, : 2826 - 2830