Metraipolis › archive › dc_025a646f464d

ALDER: A Single-Loop Augmented-Lagrangian Damped Extragradient Method for Nonconvex--Concave Minimax Problems with Nonlinear Coupled Constraints — arXiv:2611.00691

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.00691
License (as archived)
CC0-1.0
Archived
2026-11-03T18:39:27.512Z
SHA-256 of the archived text
cd19609d5418a12c912e15f3d8490201b91850f74cc8c1fb57d1acb392b224cf
Stable URL of this page
https://metraipolis.com/documento/dc_025a646f464d

How to cite

ALDER: A Single-Loop Augmented-Lagrangian Damped Extragradient Method for Nonconvex--Concave Minimax Problems with Nonlinear Coupled Constraints — arXiv:2611.00691 — arXiv (en), https://arxiv.org/abs/2611.00691 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_025a646f464d (Metraipolis archive dc_025a646f464d, sha256 cd19609d5418a12c912e15f3d8490201b91850f74cc8c1fb57d1acb392b224cf)
BibTeX
@misc{dc025a646f464d,
  title = {ALDER: A Single-Loop Augmented-Lagrangian Damped Extragradient Method for Nonconvex--Concave Minimax Problems with Nonlinear Coupled Constraints — arXiv:2611.00691},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00691},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_025a646f464d; sha256 cd19609d5418a12c912e15f3d8490201b91850f74cc8c1fb57d1acb392b224cf},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00691. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

ALDER, a single-loop augmented-Lagrangian damped extragradient method, is proposed for smooth nonconvex--concave minimax problems with nonlinear coupled inequality constraints. Within an augmented-Lagrangian framework, ALDER combines prediction--correction steps for the primal variables with explicit projected-and-relaxed multiplier updates in a single loop. The penalty parameter is fixed throughout each run, eliminating inner-loop subproblem solves and iterative penalty updates. We establish uniform boundedness of the relaxed multiplier sequence and, under an extended Mangasarian--Fromovitz constraint qualification, boundedness of the projected output multiplier. Building on these bounds, we show that ALDER finds an $\varepsilon$-KKT point within $\mathcal{O}(\varepsilon^{-7/2})$ complete first-order oracle evaluations in the strongly concave setting and $\mathcal{O}(\varepsilon^{-4})$ in the concave setting. These bounds improve upon the best known complexity bounds for multi-loop algorithms for this problem class, achieved by FAL, by removing a $\log(1/\varepsilon)$ factor, while retaining a single-loop update structure.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Optimization and Control (math.OC) ; Machine Learning (cs.LG); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2611.00691 — 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 2026-11-03T18:12:54.700Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).