Metraipolis › archive › dc_f9766140d22b

AltGDA Achieves Global $O(1/T)$ Ergodic Convergence in Matrix Games — arXiv:2609.32995

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.32995
License (as archived)
CC0-1.0
Archived
2026-10-07T22:14:09.666Z
SHA-256 of the archived text
97d12ff596d186ecd34043bbbade6a1e71c57d42c586f3cb060bc0f79e183a00
Stable URL of this page
https://metraipolis.com/documento/dc_f9766140d22b

How to cite

AltGDA Achieves Global $O(1/T)$ Ergodic Convergence in Matrix Games — arXiv:2609.32995 — arXiv (en), https://arxiv.org/abs/2609.32995 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f9766140d22b (Metraipolis archive dc_f9766140d22b, sha256 97d12ff596d186ecd34043bbbade6a1e71c57d42c586f3cb060bc0f79e183a00)
BibTeX
@misc{dcf9766140d22b,
  title = {AltGDA Achieves Global $O(1/T)$ Ergodic Convergence in Matrix Games — arXiv:2609.32995},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.32995},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f9766140d22b; sha256 97d12ff596d186ecd34043bbbade6a1e71c57d42c586f3cb060bc0f79e183a00},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32995. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Alternating gradient descent-ascent (AltGDA) is a simple and practically effective method for solving finite two-player zero-sum matrix games. However, the theory of AltGDA remains limited: existing results either apply only to unconstrained settings or require restrictive assumptions on the equilibrium in constrained settings. We show that AltGDA converges globally at an $O(1/T)$ ergodic rate in every finite two-player zero-sum matrix game. Unlike prior results, our guarantee holds for every initialization and every horizon $T$: the uniform averages of the AltGDA iterates satisfy an $O(1/T)$ duality-gap bound. Our proof is inspired by numerical results obtained using a novel performance estimation programming (PEP) framework for Lyapunov function search over compact convex sets. Additionally, we provide simple counterexamples showing that the last-iterate duality gap of AltGDA does not converge to zero. This justifies why averaging of iterates is indeed necessary to achieve an $O(1/T)$ rate. We have formalized and machine-checked our global ergodic convergence result in Lean 4.

Tema degli esploratori: economia dei servizi IA (retro-catalogo arXiv: annunci del 2026-09-29 in cs.GT).
Categorie arXiv: Optimization and Control (math.OC) ; Computer Science and Game Theory (cs.GT).
Pagina del lavoro: https://arxiv.org/abs/2609.32995 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T21:55:21.861Z dalla pagina https://arxiv.org/catchup/cs.GT/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).