Hinge Loss

Hinge Loss is a loss function used in classification tasks that belongs to the family of margin-based loss functions, distinguished by its piecewise linear formulation which penalizes predictions based on their deviation from a margin boundary, specifically assigning zero loss to correct classifications that exceed the margin and linear loss otherwise.

325

Publications

27.8K

Citations

944

Authors

392

Institutions

Publications per year

2017–2026

142

Authors

944

  1. IW
    Ivor W. Tsang

    University of Technology Sydney, Australia

    6 publications · 526 citations

    6

    h-index

  2. DT
    Dacheng Tao

    The University of Sydney, Australia

    5 publications · 139 citations

    5

    h-index

  3. MS
    Masashi Sugiyama

    Tokyo Institute of Technology, Japan

    5 publications · 640 citations

    5

    h-index

  4. HZ
    Hui Zou

    University of Minnesota, United States

    4 publications · 308 citations

    4

    h-index

  5. DZ
    Ding‐Xuan Zhou

    City University of Hong Kong, Hong Kong SAR China

    4 publications · 214 citations

    4

    h-index

1–5 of 944

Venues

  1. arXiv (Cornell University)

    Repository · 29 publications · 869 citations

    16

    h-index

  2. 9

    h-index

  3. IEEE Access

    6 publications · 166 citations

    6

    h-index

  4. PLoS ONE

    6 publications · 118 citations

    6

    h-index

  5. Neural Information Processing Systems

    Conference · 6 publications · 399 citations

    6

    h-index

1–5