Metraipolis › archive › dc_fa1644b8499b

FedRSPO+: A Heterogeneity-aware Algorithm for Decision-focused Federated Learning — arXiv:2610.09091

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.09091
License (as archived)
CC0-1.0
Archived
2026-10-08T11:56:21.160Z
SHA-256 of the archived text
703e5893a441fc46a672cf0fa157a13df524a8e2f5b1dd381355f1b3efd7f887
Stable URL of this page
https://metraipolis.com/documento/dc_fa1644b8499b

How to cite

FedRSPO+: A Heterogeneity-aware Algorithm for Decision-focused Federated Learning — arXiv:2610.09091 — arXiv (en), https://arxiv.org/abs/2610.09091 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fa1644b8499b (Metraipolis archive dc_fa1644b8499b, sha256 703e5893a441fc46a672cf0fa157a13df524a8e2f5b1dd381355f1b3efd7f887)
BibTeX
@misc{dcfa1644b8499b,
  title = {FedRSPO+: A Heterogeneity-aware Algorithm for Decision-focused Federated Learning — arXiv:2610.09091},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.09091},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fa1644b8499b; sha256 703e5893a441fc46a672cf0fa157a13df524a8e2f5b1dd381355f1b3efd7f887},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.09091. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Decision-focused learning (DFL) trains predictive models for downstream optimization, but existing methods largely assume centralized data. In cross-silo settings, federated learning offers a natural alternative, yet standard federated methods optimize prediction over decision quality and do not address heterogeneity in downstream objectives or feasible sets. This heterogeneity is especially challenging for DFL because small perturbations in polyhedral problems can cause discontinuous changes in optimal decisions, destabilizing client updates and aggregation. We propose FedRSPO+, a heterogeneity-aware framework for decision-focused federated learning, built on RSPO+, a regularized predict-then-optimize surrogate that smooths the decision map through projection. We show that RSPO+ upper bounds decision error and regret for the regularized decision and, under exact regularization and consistent LP solution selection, for the original LP decision. We further derive cross-client heterogeneity bounds that depend on both objective and feasible-set heterogeneity, vanish at homogeneity, and require no strong convexity. FedRSPO+ uses an annealed, modular training procedure compatible with standard federated personalization and aggregation methods. Experiments on synthetic knapsack, shortest-path, and real-world energy pricing tasks compare against prediction-only federated learning and DFL baselines under varying heterogeneity and communication budgets. Results suggest that smoothing is a useful ingredient for stable collaborative decision learning and provide a heterogeneity-aware foundation for federated DFL.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Optimization and Control (math.OC); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2610.09091 — 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 2026-10-08T10:50:37.653Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).