Saddle Point Optimization

Saddle Point Optimization is a mathematical optimization framework that addresses problems involving the simultaneous minimization and maximization of a function over distinct variable sets, typically to find stable equilibria in non-convex machine learning objectives such as those in adversarial training and min-max formulations.

638

Publications

38.8K

Citations

1.2K

Authors

521

Institutions

Publications per year

2017–2026

254

Authors

1.2K

  1. GL
    Guanghui Lan

    Georgia Institute of Technology, United States

    9 publications · 2.9K citations

    9

    h-index

  2. AR
    Alejandro Ribeiro

    University of Pennsylvania, United States

    9 publications · 366 citations

    9

    h-index

  3. AK
    Alec Koppel

    DEVCOM Army Research Laboratory, United States

    9 publications · 338 citations

    9

    h-index

  4. SL
    Simon Lacoste-Julien

    Université de Montréal, Canada

    8 publications · 410 citations

    8

    h-index

  5. TY
    Tianbao Yang

    University of Iowa, United States

    8 publications · 235 citations

    8

    h-index

1–5 of 1.2K

Venues

  1. arXiv (Cornell University)

    Repository · 99 publications · 4.3K citations

    37

    h-index

  2. IEEE Transactions on Signal Processing

    14 publications · 968 citations

    15

    h-index

  3. SIAM Journal on Optimization

    15 publications · 3.2K citations

    15

    h-index

  4. IEEE Transactions on Automatic Control

    12 publications · 1.3K citations

    12

    h-index

  5. Journal of Optimization Theory and Applications

    14 publications · 933 citations

    12

    h-index

1–5