Metraipolis › archive › dc_71e4adf03495

Compressed Per-Player Local Methods for Multiplayer Federated Learning: Exact Convergence via Increment Sharing — arXiv:2611.08686

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.08686
License (as archived): CC0-1.0
Archived: 2026-11-09T22:41:49.744Z
SHA-256 of the archived text: f087bcab53acee94ba822c2ca6686bf74b42e7235a6ad5891b6b39529ecc763a
Stable URL of this page: https://metraipolis.com/documento/dc_71e4adf03495

How to cite

Compressed Per-Player Local Methods for Multiplayer Federated Learning: Exact Convergence via Increment Sharing — arXiv:2611.08686 — arXiv (en), https://arxiv.org/abs/2611.08686 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_71e4adf03495 (Metraipolis archive dc_71e4adf03495, sha256 f087bcab53acee94ba822c2ca6686bf74b42e7235a6ad5891b6b39529ecc763a)

BibTeX

@misc{dc71e4adf03495,
  title = {Compressed Per-Player Local Methods for Multiplayer Federated Learning: Exact Convergence via Increment Sharing — arXiv:2611.08686},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.08686},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_71e4adf03495; sha256 f087bcab53acee94ba822c2ca6686bf74b42e7235a6ad5891b6b39529ecc763a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.08686. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multiplayer Federated Learning (MpFL), introduced by Yoon et al. (2025), extends classical federated learning to settings where clients are rational players in a game with individual objectives and strategies, seeking an equilibrium. A natural baseline is Per-Player Local SGD (PEARL-SGD), where each player performs several local SGD steps before exchanging strategies through a central server. However, the original PEARL-SGD formulation does not extend cleanly to compressed communication. Directly compressing the players' strategies can prevent convergence to the equilibrium, even with deterministic gradients. To address this issue, we reformulate PEARL-SGD so that players communicate local strategy increments rather than the strategies themselves. Without compression, the two formulations are equivalent, but with compression, increment sharing preserves exact convergence, allowing us to design the communication-efficient compressed PEARL-SGD (C-PEARL-SGD). Beyond compression, we also consider variance reduction as another axis of improvement, introducing PEARL-SVRG and its compressed variant C-PEARL-SVRG. Under the original MpFL assumptions, we establish convergence guarantees for all variants through a unified parametric inequality. Numerical experiments, including distributed spectrum sensing, demonstrate the practical benefits of our methods over vanilla PEARL-SGD.

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).
Pagina del lavoro: https://arxiv.org/abs/2611.08686 — 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 2026-11-09T22:33:47.170Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).