Decoupled SGDA for Games with Intermittent Strategy Communication

We introduceDecoupled SGDA, a novel adaptation of Stochastic Gradient Descent Ascent (SGDA) tailored for multiplayer games with intermittent strategy communication. Unlike prior methods, Decoupled SGDA enables players to update strategies locally using outdated opponent strategies, significantly reducing communication overhead. For Strongly-Convex-Strongly-Concave (SCSC) games, it achieves near-optimal communication complexity comparable to the best-known GDA rates. Forweakly coupledgames where the interaction between players is lower relative to the non-interactive part of the game, Decoupled SGDA significantly reduces communication costs compared to standard SGDA. Additionally,Decoupled SGDAoutperforms federated minimax approaches in noisy, imbalanced settings. These results establishDecoupled SGDAas a transformative approach for distributed optimization in resource-constrained environments.