Decoupled SGDA for Games with Intermittent Strategy Communication

Ali Zindari, Parham Yazdkhasti, Anton Rodomanov, Tatjana Chavdarova, Sebastian U Stich

Keywords: optimization, minimax optimization, distributed games, distributed optimization

Abstract:

We focus on reducing communication overhead in multiplayer games, where frequently exchanging strategies between players is not feasible and players have noisy or outdated strategies of the other players.
We propose \textit{Decoupled SGDA}, an extension of Stochastic Gradient Descent Ascent (SGDA), where players perform independent updates using outdated strategies of opponents, with periodic strategy synchronization.
For Strongly-Convex-Strongly-Concave (SCSC) games, we demonstrate that Decoupled SGDA achieves near-optimal communication complexity comparable to the best-known GDA rates.
For \emph{weakly coupled} games where the interaction between players is lower relative to non-interactive part of the game, Decoupled SGDA significantly reduces communication costs compared to standard SGDA.
Our findings extend to multi-player games. To provide insights into the effect of communication frequency and convergence, we extensively study the convergence of Decoupled SGDA for quadratic minimax problems.
Lastly, in settings where the noise over the players is imbalanced, Decoupled SGDA significantly outperforms federated minimax methods.

Primary Area: optimization

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 12030