Decoupled SGDA for Games with Intermittent Strategy Communication

Ali Zindari, Parham Yazdkhasti, Anton Rodomanov, Tatjana Chavdarova, Sebastian U Stich
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:80662-80707, 2025.

Abstract

We introduce Decoupled 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 Unlike prior methods, Decoupled SGDA enables players to update strategies locally using outdated opponent strategies, significantly reducing communication overhead.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. For weakly coupled games 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 SGDA outperforms federated minimax approaches in noisy, imbalanced settings. These results establish Decoupled SGDA as a transformative approach for distributed optimization in resource-constrained environments.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-zindari25a, title = {Decoupled {SGDA} for Games with Intermittent Strategy Communication}, author = {Zindari, Ali and Yazdkhasti, Parham and Rodomanov, Anton and Chavdarova, Tatjana and Stich, Sebastian U}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {80662--80707}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/zindari25a/zindari25a.pdf}, url = {https://proceedings.mlr.press/v267/zindari25a.html}, abstract = {We introduce Decoupled 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 Unlike prior methods, Decoupled SGDA enables players to update strategies locally using outdated opponent strategies, significantly reducing communication overhead.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. For weakly coupled games 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 SGDA outperforms federated minimax approaches in noisy, imbalanced settings. These results establish Decoupled SGDA as a transformative approach for distributed optimization in resource-constrained environments.} }
Endnote
%0 Conference Paper %T Decoupled SGDA for Games with Intermittent Strategy Communication %A Ali Zindari %A Parham Yazdkhasti %A Anton Rodomanov %A Tatjana Chavdarova %A Sebastian U Stich %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-zindari25a %I PMLR %P 80662--80707 %U https://proceedings.mlr.press/v267/zindari25a.html %V 267 %X We introduce Decoupled 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. For weakly coupled games 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 SGDA outperforms federated minimax approaches in noisy, imbalanced settings. These results establish Decoupled SGDA as a transformative approach for distributed optimization in resource-constrained environments.
APA
Zindari, A., Yazdkhasti, P., Rodomanov, A., Chavdarova, T. & Stich, S.U.. (2025). Decoupled SGDA for Games with Intermittent Strategy Communication. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:80662-80707 Available from https://proceedings.mlr.press/v267/zindari25a.html.

Related Material