Margin-based Loss

Margin-Based Loss is a type of loss function in machine learning that penalizes predictions based on the margin between the confidence scores of correct and incorrect classifications, differing from other loss functions by explicitly enforcing a separation boundary to enhance generalization.

264

Publications

21.7K

Citations

770

Authors

275

Institutions

Publications per year

2017–2026

170

Variants

Margin Loss

Authors

770

  1. ZL
    Zhen Lei

    Chinese Academy of Sciences, China

    5 publications · 196 citations

    5

    h-index

  2. WY
    Wenming Yang

    Tsinghua University, China

    4 publications · 115 citations

    4

    h-index

  3. HS
    Hailin Shi

    Chinese Academy of Sciences, China

    4 publications · 248 citations

    4

    h-index

  4. XW
    Xiaobo Wang

    Chinese Academy of Sciences, China

    4 publications · 255 citations

    4

    h-index

  5. XC
    Xueqi Cheng

    Chinese Academy of Sciences, China

    4 publications · 162 citations

    4

    h-index

1–5 of 770

Venues

  1. arXiv (Cornell University)

    Repository · 52 publications · 3.4K citations

    25

    h-index

  2. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 8 publications · 624 citations

    8

    h-index

  3. 7

    h-index

  4. Pattern Recognition

    7 publications · 280 citations

    7

    h-index

  5. 5

    h-index

1–5