Metraipolis › archive › dc_500cb8484cd9

Relative-Error Composite Federated Optimization with One Server-Side Proximal Step per Round — arXiv:2611.04448

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.04448
License (as archived): CC0-1.0
Archived: 2026-11-04T12:45:18.651Z
SHA-256 of the archived text: 59365da061de8dbf6a65306eb5bb222a5979f01aed8abbf8f6bae5241a8d159a
Stable URL of this page: https://metraipolis.com/documento/dc_500cb8484cd9

How to cite

Relative-Error Composite Federated Optimization with One Server-Side Proximal Step per Round — arXiv:2611.04448 — arXiv (en), https://arxiv.org/abs/2611.04448 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_500cb8484cd9 (Metraipolis archive dc_500cb8484cd9, sha256 59365da061de8dbf6a65306eb5bb222a5979f01aed8abbf8f6bae5241a8d159a)

BibTeX

@misc{dc500cb8484cd9,
  title = {Relative-Error Composite Federated Optimization with One Server-Side Proximal Step per Round — arXiv:2611.04448},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.04448},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_500cb8484cd9; sha256 59365da061de8dbf6a65306eb5bb222a5979f01aed8abbf8f6bae5241a8d159a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04448. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We consider deterministic composite federated optimization, in which distributed smooth client objectives are combined with a shared, possibly nonsmooth, regularizer. We propose Relative-Error Composite FedDyn (REC-FedDyn), an inexact method that supports partial participation, with one server-side proximal evaluation per communication round. REC-FedDyn employs a directly testable relative-error criterion that allows each client to independently control the accuracy of its local subproblem, without a server-side acceptance test. We establish almost-sure iterate convergence for strongly convex and convex problems, almost-sure asymptotic stationarity for nonconvex problems, and communication and parallel gradient-evaluation complexity bounds, all under partial participation and without assuming bounded data heterogeneity. Experiments on image inpainting, fMRI prediction, and neural-network classification with structured regularization demonstrate efficiency and robustness across levels of data heterogeneity and client participation.

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/2611.04448 — 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 2026-11-04T12:31:32.256Z dalla pagina https://arxiv.org/list/math.OC/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).