Regularized Loss

Regularized Loss is a loss function that incorporates an additional penalty term derived from a regularization method to control model complexity and prevent overfitting by balancing empirical risk minimization with structural risk minimization.

375

Publications

29.2K

Citations

1K

Authors

405

Institutions

Publications per year

2017–2026

197

Variants

Regularized Loss Function

Authors

1K

  1. SS
    Shai Shalev‐Shwartz

    Hebrew University of Jerusalem, Israel

    10 publications · 2K citations

    10

    h-index

  2. PR
    Peter Richtárik

    University of Edinburgh, United Kingdom

    6 publications · 172 citations

    6

    h-index

  3. MT
    Martin Takáč

    Lehigh University, United States

    6 publications · 356 citations

    6

    h-index

  4. TZ
    Tong Zhang

    Tencent (China), China

    6 publications · 932 citations

    6

    h-index

  5. TP
    Tomaso Poggio

    Massachusetts Institute of Technology, United States

    5 publications · 665 citations

    5

    h-index

1–5 of 1K

Venues

  1. arXiv (Cornell University)

    Repository · 65 publications · 4.1K citations

    31

    h-index

  2. Neurocomputing

    12 publications · 511 citations

    11

    h-index

  3. Neural Information Processing Systems

    Conference · 9 publications · 935 citations

    9

    h-index

  4. Pattern Recognition

    8 publications · 364 citations

    8

    h-index

  5. IEEE Access

    7 publications · 198 citations

    6

    h-index

1–5