Metraipolis › archive › dc_5a3a06cc8a5a

CovFedAvg: Local Low-Loss Curves and Federated Model Selection — arXiv:2610.39902

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.39902
License (as archived)
CC0-1.0
Archived
2026-10-31T06:14:44.332Z
SHA-256 of the archived text
b0250007e759d1954f6b635b2f53645e5a8d600d3f9f1753d8049ac497bb8bb3
Stable URL of this page
https://metraipolis.com/documento/dc_5a3a06cc8a5a

How to cite

CovFedAvg: Local Low-Loss Curves and Federated Model Selection — arXiv:2610.39902 — arXiv (en), https://arxiv.org/abs/2610.39902 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5a3a06cc8a5a (Metraipolis archive dc_5a3a06cc8a5a, sha256 b0250007e759d1954f6b635b2f53645e5a8d600d3f9f1753d8049ac497bb8bb3)
BibTeX
@misc{dc5a3a06cc8a5a,
  title = {CovFedAvg: Local Low-Loss Curves and Federated Model Selection — arXiv:2610.39902},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.39902},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5a3a06cc8a5a; sha256 b0250007e759d1954f6b635b2f53645e5a8d600d3f9f1753d8049ac497bb8bb3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.39902. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Clients observing different parts of a prediction task may learn locally equivalent models with incompatible behavior outside their observed support. We study whether redundant models permit local low-loss paths toward a compatible shared model. CovFedAvg retains local models and curve controls on clients, fits a common endpoint through aggregated gradient contributions, and selects an actual candidate model using distributed training losses. No centralized calibration examples or client-to-client sample exchange are required. Exact selection guarantees no higher evaluated training loss than the previous model and the current-round FedAvg candidate; this is not a global-optimality, stationarity, generalization, or differential-privacy guarantee. We state conditional client-compatibility and approximate-selection bounds and retain corrected transformation identities and a separate full-gradient safeguard theorem for reference algorithms. A complementary input-support example recovers the shared absolute-value regression, while matched direct fine-tuning also solves it. Across a synthetic support task, recorded activity-recognition subjects, and participating and future gas-sensor batches, we evaluate five methods, five seeds, two network widths, and 20 rounds without calibration data. At width 16, CovFedAvg raises participating-Gas macro balanced accuracy from FedAvg's 88.88% to 89.84%; matched distributed fine-tuning reaches 91.65%. Results support feasibility and modest gains over FedAvg, but do not establish a curve-specific advantage over equally costly optimization. Exact-sum numerical experiments establish data flow; end-to-end privacy requires additional mechanisms and analysis.

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/2610.39902 — 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 2026-10-31T06:07:08.742Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).