Metraipolis › archive › dc_0922fd17845b

Single-Loop Stochastic Projected Damped Extragradient Methods for Stochastic Nonconvex--(Strongly) Concave Minimax Optimization — arXiv:2609.21747

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.21747
License (as archived)
CC0-1.0
Archived
2026-10-10T01:47:35.311Z
SHA-256 of the archived text
7c4f4119c9e650793738e4a3efe97a0210cd2ea8b313352bc7c5de3e2bc65890
Stable URL of this page
https://metraipolis.com/documento/dc_0922fd17845b

How to cite

Single-Loop Stochastic Projected Damped Extragradient Methods for Stochastic Nonconvex--(Strongly) Concave Minimax Optimization — arXiv:2609.21747 — arXiv (en), https://arxiv.org/abs/2609.21747 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0922fd17845b (Metraipolis archive dc_0922fd17845b, sha256 7c4f4119c9e650793738e4a3efe97a0210cd2ea8b313352bc7c5de3e2bc65890)
BibTeX
@misc{dc0922fd17845b,
  title = {Single-Loop Stochastic Projected Damped Extragradient Methods for Stochastic Nonconvex--(Strongly) Concave Minimax Optimization — arXiv:2609.21747},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.21747},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0922fd17845b; sha256 7c4f4119c9e650793738e4a3efe97a0210cd2ea8b313352bc7c5de3e2bc65890},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.21747. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We develop single-loop stochastic projected damped extragradient methods for stochastic nonconvex--(strongly) concave minimax optimization, with complexity guarantees for both game stationarity (GS) and optimization stationarity (OS). Our approach combines a stochastic projected damped extragradient (SPDE) method with a recursive variance-reduced variant, VR-SPDE, both of which retain a single-loop structure. Under an unbiased stochastic gradient oracle with uniformly bounded variance, SPDE finds an $\varepsilon$-game-stationary point with stochastic first-order oracle (SFO) complexities of $O(\kappa\varepsilon^{-4})$ and $O(\varepsilon^{-5})$ in the nonconvex--strongly concave and nonconvex--concave settings, respectively, where $\kappa=L/\mu$. Under an additional mean-square Lipschitz condition on the stochastic gradients, VR-SPDE improves these GS complexities to $O(\kappa^{3/2}\varepsilon^{-3})$ and $O(\varepsilon^{-9/2})$, respectively. For an $\varepsilon$-optimization-stationary point, SPDE achieves SFO complexities of $O(\kappa\varepsilon^{-4})$ and $O(\varepsilon^{-6})$, while VR-SPDE achieves $O(\kappa^{3/2}\varepsilon^{-3})$ and $O(\varepsilon^{-6})$, in the two settings, respectively. These OS guarantees match the best-known bounds achieved by multi-loop methods while preserving a single-loop implementation. To the best of our knowledge, our results provide the best-known SFO complexity guarantees among single-loop stochastic first-order methods for the respective stationarity criteria and problem classes.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-21 in cs.LG).
Categorie arXiv: Optimization and Control (math.OC) ; Machine Learning (cs.LG); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2609.21747 — 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 2026-10-10T01:14:16.713Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).