Metraipolis › archive › dc_244be495c5a6

Cordial Learning: Distributed Training with Correlated Data — arXiv:2610.03330

Source
arXiv
Original
https://arxiv.org/abs/2610.03330
License (as archived)
CC0-1.0
Archived
2026-10-05T22:50:37.157Z
SHA-256 of the archived text
288fca5dd281ccf92ec5dc42540fe03b35c9ac94d3a636f226e0bf08bcfb7f28
Stable URL of this page
https://metraipolis.com/documento/dc_244be495c5a6

How to cite

Cordial Learning: Distributed Training with Correlated Data — arXiv:2610.03330 — arXiv, https://arxiv.org/abs/2610.03330 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_244be495c5a6 (Metraipolis archive dc_244be495c5a6, sha256 288fca5dd281ccf92ec5dc42540fe03b35c9ac94d3a636f226e0bf08bcfb7f28)
BibTeX
@misc{dc244be495c5a6,
  title = {Cordial Learning: Distributed Training with Correlated Data — arXiv:2610.03330},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.03330},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_244be495c5a6; sha256 288fca5dd281ccf92ec5dc42540fe03b35c9ac94d3a636f226e0bf08bcfb7f28},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.03330. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We consider a distributed learning task with agents that have correlated data. Specifically, the label of an agent depends on the input of other agents for the same sample, and these inputs are also correlated. Correlated data is the reality when agents share the same environment. Existing decentralized methods, such as federated learning, ignore the structure of the problem and perform poorly on correlated data. On the other hand, centralized approaches are infeasible due to privacy and communication constraints. We introduce cordial (correlated and distributed) learning to address this gap by sharing only low-dimensional outputs between the agents while training local models to extract informative signals from peers. This distributed learning induces a game in which the loss function of each agent depends on the models of others. Assuming a linear model, we prove that cordial learning converges with probability one to a globally optimal solution, despite the nonconvex global objective. Experiments on structured multi-digit MNIST tasks demonstrate that cordial learning remains highly effective even in highly nonlinear settings.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.03330 — 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 2026-10-05T22:45:55.853Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).