IDEAS home Printed from https://ideas.repec.org/p/hal/journl/hal-05053682.html
   My bibliography  Save this paper

Optimistic Gradient Descent Ascent in General-Sum Bilinear Games

Author

Listed:
  • Etienne de Montbrun

    (TSE-R - Toulouse School of Economics - UT Capitole - Université Toulouse Capitole - UT - Université de Toulouse - EHESS - École des hautes études en sciences sociales - CNRS - Centre National de la Recherche Scientifique - INRAE - Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement)

  • Jerôme Renault

    (TSE-R - Toulouse School of Economics - UT Capitole - Université Toulouse Capitole - UT - Université de Toulouse - EHESS - École des hautes études en sciences sociales - CNRS - Centre National de la Recherche Scientifique - INRAE - Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement)

Abstract

We study the convergence of optimistic gradient descent ascent in unconstrained bilinear games. For zero-sum games, we prove exponential convergence to a saddle-point for any payoff matrix, and provide the exact ratio of convergence as a function of the step size. Then, we introduce OGDA for general-sum games and show that, in many cases, either OGDA converges exponentially fast to a Nash equilibrium, or the payoffs for both players converge to . We also show how to increase drastically the speed of convergence of a zero-sum problem by introducing a general-sum game using the Moore-Penrose inverse of the original payoff matrix. To our knowledge, this shows for the first time that general-sum games can be used to optimally improve algorithms designed for min-max problems. We illustrate our results on a toy example of a Wasserstein GAN. Finally, we show how the approach could be extended to the more general class of "hidden bilinear games".

Suggested Citation

  • Etienne de Montbrun & Jerôme Renault, 2025. "Optimistic Gradient Descent Ascent in General-Sum Bilinear Games," Post-Print hal-05053682, HAL.
    • Handle: RePEc:hal:journl:hal-05053682
    DOI: 10.3934/jdg.2024030
    as

    Download full text from publisher

    To our knowledge, this item is not available for download. To find whether it is available, there are three options:
    1. Check below whether another version of this item is available online.
    2. Check on the provider's web page whether it is in fact available.
    3. Perform a search for a similarly titled item that would be available.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:hal:journl:hal-05053682. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    We have no bibliographic references for this item. You can help adding them by using this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: CCSD (email available below). General contact details of provider: https://hal.archives-ouvertes.fr/ .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.