Loss Function

In machine learning, a Loss Function is a real-valued objective function that, given a model’s prediction and the corresponding ground-truth target, returns a numerical measure of prediction error that is minimized during training.

6.9K

Publications

618.4K

Citations

15.6K

Authors

2.8K

Institutions

Publications per year

2017–2026

4.7K

Authors

15.6K

  1. MS
    Masashi Sugiyama

    Tokyo Institute of Technology, Japan

    40 publications · 2.1K citations

    24

    h-index

  2. PL
    Peter L. Bartlett

    University of California, Berkeley, United States

    26 publications · 4.4K citations

    19

    h-index

  3. SS
    Shai Shalev‐Shwartz

    Hebrew University of Jerusalem, Israel

    19 publications · 4.1K citations

    18

    h-index

  4. DZ
    Ding‐Xuan Zhou

    City University of Hong Kong, Hong Kong SAR China

    26 publications · 1.4K citations

    18

    h-index

  5. GN
    Gang Niu

    Xi'an Jiaotong University, China

    21 publications · 1.4K citations

    18

    h-index

1–5 of 15.6K

Venues

  1. arXiv (Cornell University)

    Repository · 1.3K publications · 98.5K citations

    130

    h-index

  2. IEEE Transactions on Pattern Analysis and Machine Intelligence

    TPAMI · 90 publications · 10.6K citations

    48

    h-index

  3. Neurocomputing

    109 publications · 24.9K citations

    45

    h-index

  4. 42

    h-index

  5. Neural Networks

    86 publications · 47.3K citations

    42

    h-index

1–5