Minimax Optimization

Minimax Optimization is a mathematical optimization framework that, within the context of machine learning, seeks to find optimal decision rules by minimizing the maximum possible loss, thereby distinguishing itself from conventional optimization paradigms through its adversarial structure that models worst-case scenario minimization.

1.8K

Publications

118.7K

Citations

3.4K

Authors

1.1K

Institutions

Publications per year

2017–2026

539

Authors

3.4K

  1. MI
    Michael I. Jordan

    University of California, Berkeley, United States

    17 publications · 2.5K citations

    17

    h-index

  2. JB
    J.W. Bandler

    McMaster University, Canada

    19 publications · 728 citations

    14

    h-index

  3. KH
    Kristoffer H. Madsen

    Technical University of Denmark, Denmark

    11 publications · 561 citations

    11

    h-index

  4. JD
    Jason D. Lee

    University of Southern California, United States

    11 publications · 1.1K citations

    11

    h-index

  5. TB
    Tamer Başar

    University of Illinois Urbana-Champaign, United States

    10 publications · 1.4K citations

    10

    h-index

1–5 of 3.4K

Venues

  1. arXiv (Cornell University)

    Repository · 248 publications · 12.3K citations

    56

    h-index

  2. The Annals of Statistics

    60 publications · 9.6K citations

    36

    h-index

  3. IEEE Transactions on Automatic Control

    35 publications · 5.1K citations

    25

    h-index

  4. IEEE Transactions on Signal Processing

    38 publications · 4.5K citations

    23

    h-index

  5. Journal of Optimization Theory and Applications

    44 publications · 1.7K citations

    23

    h-index

1–5