Generalization Error

Generalization Error is the expected value of the discrepancy between a model's predicted outputs and the true outputs on unseen data, serving as a measure of the model's ability to perform accurately on new instances drawn from the same underlying distribution, thereby distinguishing it from training error and reflecting the effectiveness of learning in the context of supervised learning, overfitting, underfitting, model selection, and the bias-variance tradeoff.

1.2K

Publications

98.6K

Citations

2.9K

Authors

867

Institutions

Publications per year

2017–2026

597

Authors

2.9K

  1. DT
    Dacheng Tao

    The University of Sydney, Australia

    20 publications · 1.6K citations

    19

    h-index

  2. WW
    Wing W. Y. Ng

    South China University of Technology, China

    25 publications · 1.1K citations

    16

    h-index

  3. TL
    Tongliang Liu

    The University of Sydney, Australia

    15 publications · 761 citations

    15

    h-index

  4. DY
    Daniel Yeung

    South China University of Technology, China

    14 publications · 556 citations

    12

    h-index

  5. MS
    Masashi Sugiyama

    Tokyo Institute of Technology, Japan

    13 publications · 921 citations

    12

    h-index

1–5 of 2.9K

Venues

  1. arXiv (Cornell University)

    Repository · 265 publications · 15.5K citations

    63

    h-index

  2. Neural Computation

    40 publications · 6.5K citations

    30

    h-index

  3. IEEE Transactions on Pattern Analysis and Machine Intelligence

    TPAMI · 23 publications · 6.5K citations

    22

    h-index

  4. Neural Information Processing Systems

    Conference · 24 publications · 1.6K citations

    18

    h-index

  5. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 24 publications · 981 citations

    16

    h-index

1–5