Metraipolis › archive › dc_216881edcd61

Distributionally Robust Federated Learning with Multi-Source Data — arXiv:2609.20501

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.20501
License (as archived)
CC0-1.0
Archived
2026-10-10T04:09:06.540Z
SHA-256 of the archived text
68c33fe999f87c7d2f9d0cb2bd72e92b0f8fbdbc9cb20a167b6805ed7c9dd8f6
Stable URL of this page
https://metraipolis.com/documento/dc_216881edcd61

How to cite

Distributionally Robust Federated Learning with Multi-Source Data — arXiv:2609.20501 — arXiv (en), https://arxiv.org/abs/2609.20501 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_216881edcd61 (Metraipolis archive dc_216881edcd61, sha256 68c33fe999f87c7d2f9d0cb2bd72e92b0f8fbdbc9cb20a167b6805ed7c9dd8f6)
BibTeX
@misc{dc216881edcd61,
  title = {Distributionally Robust Federated Learning with Multi-Source Data — arXiv:2609.20501},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.20501},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_216881edcd61; sha256 68c33fe999f87c7d2f9d0cb2bd72e92b0f8fbdbc9cb20a167b6805ed7c9dd8f6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.20501. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Federated learning trains a shared model from private client data. In practice, data-generating distributions may differ, and the true mixture across clients is often unknown, making the underlying group distribution difficult to specify. Existing approaches address cross-client mixture uncertainty by optimizing against the worst-case mixture, yet assume accurate client-wise distribution estimates. However, these estimates can be unreliable when based on finite samples. To handle both cross-client mixture uncertainty and within-client distributional ambiguity, we construct a global ambiguity set as the union of admissible mixtures of local ambiguity sets. The construction allows client-specific ambiguity radii and admits a client-wise separable reformulation. Leveraging this structure, we establish a high-probability out-of-sample performance guarantee. We further develop a federated algorithm for a penalty-based reformulation and prove its convergence under milder regularity conditions. Simulations validate the algorithm's effectiveness.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-18 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Optimization and Control (math.OC).
Pagina del lavoro: https://arxiv.org/abs/2609.20501 — 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 2026-10-10T03:48:18.368Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).