Early Stopping

Early Stopping is a regularization technique in machine learning that halts the training process prematurely based on the performance on a validation set to prevent overfitting by avoiding excessive iterations that lead to model specialization on training data.

582

Publications

42K

Citations

1.8K

Authors

749

Institutions

Publications per year

2017–2026

242

Authors

1.8K

  1. DL
    David L. DeMets

    University of Wisconsin–Madison, United States

    5 publications · 477 citations

    5

    h-index

  2. LR
    Lorenzo Rosasco

    University of Genoa, Italy

    5 publications · 1.1K citations

    5

    h-index

  3. MJ
    Martin J. Wainwright

    University of California, Berkeley, United States

    5 publications · 296 citations

    5

    h-index

  4. MS
    Mahdi Soltanolkotabi

    University of Southern California, United States

    4 publications · 413 citations

    4

    h-index

  5. PB
    Péter Bauer

    Statistics Austria, Austria

    4 publications · 1.1K citations

    4

    h-index

1–5 of 1.8K

Venues

  1. arXiv (Cornell University)

    Repository · 76 publications · 3.7K citations

    32

    h-index

  2. Statistics in Medicine

    31 publications · 1.5K citations

    20

    h-index

  3. Journal of Clinical Oncology

    12 publications · 988 citations

    11

    h-index

  4. Journal of the American Statistical Association

    10 publications · 545 citations

    10

    h-index

  5. IEEE Access

    9 publications · 301 citations

    9

    h-index

1–5