On the $O(1/T)$ Convergence of Alternating Gradient Descent-Ascent in Bilinear Games

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Nan, Tianlong, Gupta, Shuvomoy Das, Iyengar, Garud, Kroer, Christian
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917300185071616
author Nan, Tianlong
Gupta, Shuvomoy Das
Iyengar, Garud
Kroer, Christian
author_facet Nan, Tianlong
Gupta, Shuvomoy Das
Iyengar, Garud
Kroer, Christian
contents We study the alternating gradient descent-ascent (AltGDA) algorithm in two-player zero-sum games. Alternating methods, where players take turns to update their strategies, have long been recognized as simple and practical approaches for learning in games, exhibiting much better numerical performance than their simultaneous counterparts. However, our theoretical understanding of alternating algorithms remains limited, and results are mostly restricted to the unconstrained setting. We show that for two-player zero-sum games that admit an interior Nash equilibrium, AltGDA converges at an $O(1/T)$ ergodic convergence rate when employing a small constant stepsize. This is the first result showing that alternation improves over the simultaneous counterpart of GDA in the constrained setting. For games without an interior equilibrium, we show an $O(1/T)$ local convergence rate with a constant stepsize that is independent of any game-specific constants. In a more general setting, we develop a performance estimation programming (PEP) framework to jointly optimize the AltGDA stepsize along with its worst-case convergence rate. The PEP results indicate that AltGDA may achieve an $O(1/T)$ convergence rate for a finite horizon $T$, whereas its simultaneous counterpart appears limited to an $O(1/\sqrt{T})$ rate.
format Preprint
id arxiv_https___arxiv_org_abs_2510_03855
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle On the $O(1/T)$ Convergence of Alternating Gradient Descent-Ascent in Bilinear Games
Nan, Tianlong
Gupta, Shuvomoy Das
Iyengar, Garud
Kroer, Christian
Computer Science and Game Theory
We study the alternating gradient descent-ascent (AltGDA) algorithm in two-player zero-sum games. Alternating methods, where players take turns to update their strategies, have long been recognized as simple and practical approaches for learning in games, exhibiting much better numerical performance than their simultaneous counterparts. However, our theoretical understanding of alternating algorithms remains limited, and results are mostly restricted to the unconstrained setting. We show that for two-player zero-sum games that admit an interior Nash equilibrium, AltGDA converges at an $O(1/T)$ ergodic convergence rate when employing a small constant stepsize. This is the first result showing that alternation improves over the simultaneous counterpart of GDA in the constrained setting. For games without an interior equilibrium, we show an $O(1/T)$ local convergence rate with a constant stepsize that is independent of any game-specific constants. In a more general setting, we develop a performance estimation programming (PEP) framework to jointly optimize the AltGDA stepsize along with its worst-case convergence rate. The PEP results indicate that AltGDA may achieve an $O(1/T)$ convergence rate for a finite horizon $T$, whereas its simultaneous counterpart appears limited to an $O(1/\sqrt{T})$ rate.
title On the $O(1/T)$ Convergence of Alternating Gradient Descent-Ascent in Bilinear Games
topic Computer Science and Game Theory
url https://arxiv.org/abs/2510.03855