Unified Binary and Multiclass Margin-Based Classification

被引:0
|
作者
Wang, Yutong [1 ,2 ]
Scott, Clayton [1 ,3 ]
机构
[1] Univ Michigan, Dept Elect Engn & Comp Sci, Ann Arbor, MI 48109 USA
[2] Univ Michigan, Michigan Inst Data Sci, Ann Arbor, MI 48109 USA
[3] Univ Michigan, Dept Stat, Ann Arbor, MI 48109 USA
基金
美国国家科学基金会;
关键词
Classification; loss functions; consistency; margins; label encodings; ALGORITHMS;
D O I
暂无
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
The notion of margin loss has been central to the development and analysis of algorithms for binary classification. To date, however, there remains no consensus as to the analogue of the margin loss for multiclass classification. In this work, we show that a broad range of multiclass loss functions, including many popular ones, can be expressed in the relative margin form, a generalization of the margin form of binary losses. The relative margin form is broadly useful for understanding and analyzing multiclass losses as shown by our prior work (Wang and Scott, 2020, 2021). To further demonstrate the utility of this way of expressing multiclass losses, we use it to extend the seminal result of Bartlett et al. (2006) on classification-calibration of binary margin losses to multiclass. We then analyze the class of Fenchel-Young losses, and expand the set of these losses that are known to be classification-calibrated.
引用
收藏
页码:1 / 51
页数:51
相关论文
共 50 条
  • [21] Online active classification via margin-based and feature-based label queries
    Zhai, Tingting
    Koriche, Frederic
    Gao, Yang
    Zhu, Junwu
    Li, Bin
    [J]. MACHINE LEARNING, 2022, 111 (06) : 2323 - 2348
  • [22] Online active classification via margin-based and feature-based label queries
    Tingting Zhai
    Frédéric Koriche
    Yang Gao
    Junwu Zhu
    Bin Li
    [J]. Machine Learning, 2022, 111 : 2323 - 2348
  • [23] New margin-based subsampling iterative technique in modified random forests for classification
    Feng, Wei
    Dauphin, Gabriel
    Huang, Wenjiang
    Quan, Yinghui
    Liao, Wenzhi
    [J]. KNOWLEDGE-BASED SYSTEMS, 2019, 182
  • [24] MARGIN-BASED SAMPLE FILTERING FOR IMAGE CLASSIFICATION USING CONVOLUTIONAL NEURAL NETWORKS
    Kaplanoglou, Pantelis I.
    Diamantaras, Konstantinos
    [J]. 2018 25TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2018, : 1 - 5
  • [25] MCVAE: Margin-based Conditional Variational Autoencoder for Relation Classification and Pattern Generation
    Ma, Fenglong
    Li, Yaliang
    Zhang, Chenwei
    Gao, Jing
    Du, Nan
    Fan, Wei
    [J]. WEB CONFERENCE 2019: PROCEEDINGS OF THE WORLD WIDE WEB CONFERENCE (WWW 2019), 2019, : 3041 - 3048
  • [26] Hypothesis Margin-Based Ensemble Method for the Classification of Noisy Remote Sensing Data
    Feng, Wei
    Gao, Xinting
    Boukir, Samia
    Xie, Zhiwei
    Quan, Yinghui
    Huang, Wenjiang
    Xing, Mengdao
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2023, 61 : 1 - 21
  • [27] Exploiting diversity of margin-based classifiers
    Romero, E
    Carreras, X
    Màrquez, L
    [J]. 2004 IEEE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-4, PROCEEDINGS, 2004, : 419 - 424
  • [28] Smooth Boosting for Margin-Based Ranking
    Moribe, Jun-ichi
    Hatano, Kohei
    Takimoto, Eiji
    Takeda, Masayuki
    [J]. ALGORITHMIC LEARNING THEORY, PROCEEDINGS, 2008, 5254 : 227 - 239
  • [29] MARGIN-BASED GENERALIZATION FOR CLASSIFICATIONS WITH INPUT NOISE
    Choe, Hi Jun
    Koh, Hayeong
    Lee, Jimin
    [J]. JOURNAL OF THE KOREAN MATHEMATICAL SOCIETY, 2022, 59 (02) : 217 - 233
  • [30] Margin-based feature selection for hyperspectral data
    Pal, Mahesh
    [J]. INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION, 2009, 11 (03): : 212 - 220