Metraipolis › archive › dc_31b29bddc014

Primal-dual forward-reflected splitting with linesearch for distributed min-max problems under local Lipschitz smoothness — arXiv:2610.23518

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.23518
License (as archived)
CC0-1.0
Archived
2026-10-19T09:37:48.201Z
SHA-256 of the archived text
e6396e66c3bc253ea24ce045a8b02b351325651af9b866a0b5108199a9d3c8dc
Stable URL of this page
https://metraipolis.com/documento/dc_31b29bddc014

How to cite

Primal-dual forward-reflected splitting with linesearch for distributed min-max problems under local Lipschitz smoothness — arXiv:2610.23518 — arXiv (en), https://arxiv.org/abs/2610.23518 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_31b29bddc014 (Metraipolis archive dc_31b29bddc014, sha256 e6396e66c3bc253ea24ce045a8b02b351325651af9b866a0b5108199a9d3c8dc)
BibTeX
@misc{dc31b29bddc014,
  title = {Primal-dual forward-reflected splitting with linesearch for distributed min-max problems under local Lipschitz smoothness — arXiv:2610.23518},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.23518},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_31b29bddc014; sha256 e6396e66c3bc253ea24ce045a8b02b351325651af9b866a0b5108199a9d3c8dc},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.23518. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We consider a network of finitely many agents aiming to cooperatively solve a convex-concave min-max problem combining nonsmooth terms with a smooth saddle function whose partial gradients are only locally Lipschitz continuous. Without requiring prior knowledge of the local Lipschitz moduli of the partial gradients, we propose a distributed proximal-reflected-gradient algorithm which incorporates a distributed backtracking procedure to adjust the stepsizes at each iteration. The algorithm is derived by reformulating the min-max problem as a composite monotone inclusion involving the sum of a maximally monotone operator, a linearly composed maximally monotone operator, and a single-valued locally Lipschitz continuous monotone operator. To solve this inclusion, we introduce a novel primal-dual forward-reflected splitting method with linesearch and establish its convergence using a Lyapunov-based analysis. In addition, when specialised to the min-max formulation, we derive an $\mathcal{O}(1/N)$ ergodic convergence rate for a consensus-penalised gap function. Finally, applying this splitting framework with mixing matrices yields our distributed method for consensus min-max optimisation.

Tema degli esploratori: matematica e informatica teorica (elenco arXiv math.OC, nuovi lavori del giorno).
Categorie arXiv: Optimization and Control (math.OC).
Pagina del lavoro: https://arxiv.org/abs/2610.23518 — 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 2026-10-19T09:33:44.744Z dalla pagina https://arxiv.org/list/math.OC/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).