Metraipolis › archive › dc_39b1d39798fe
Asking the Crowd the Right Question: Bias-Cancelling Weights for Federated Learning — arXiv:2610.04671
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.04671
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T05:32:10.715Z
- SHA-256 of the archived text
e643bbf1ca98a3e6d31a9502ee5879f9be1bd3eac2d1ec498fda68bcf2bbff42- Stable URL of this page
https://metraipolis.com/documento/dc_39b1d39798fe
How to cite
Asking the Crowd the Right Question: Bias-Cancelling Weights for Federated Learning — arXiv:2610.04671 — arXiv, https://arxiv.org/abs/2610.04671 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_39b1d39798fe (Metraipolis archive dc_39b1d39798fe, sha256 e643bbf1ca98a3e6d31a9502ee5879f9be1bd3eac2d1ec498fda68bcf2bbff42)
BibTeX
@misc{dc39b1d39798fe,
title = {Asking the Crowd the Right Question: Bias-Cancelling Weights for Federated Learning — arXiv:2610.04671},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.04671},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_39b1d39798fe; sha256 e643bbf1ca98a3e6d31a9502ee5879f9be1bd3eac2d1ec498fda68bcf2bbff42},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.04671. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
A federated objective is a weighted sum of client risks, and the weights are almost always fixed in advance. We treat them instead as the only instrument of a wisdom-of-crowds mechanism: clients are noisy views of one truth, each seeing it through an independent distortion that is unbiased across the crowd. That the optimal weights are inversely proportional to the clients' error energies is classical; we begin at the question that answer presupposes, which energies belong there and whether a crowd can recover them from itself. Excess risk on the truth is of the exact order of the aggregate bias energy, so no optimizer can repair a bad weight vector; the truth itself is identifiable only up to a linear tilt, so subtracting estimated client biases provably reproduces uniform weighting. The expected per-client second moments, however, are exactly identified from the law of the crowd's disagreement by a well-conditioned linear inversion, a step random-effects meta-analysis cannot take because a source reports once; their realized counterparts are estimable up to an incoherence floor the algorithm can measure. This yields CROWD, which reads the disagreement off the optimization trajectory at no extra cost and matches a Bayesian minimax lower bound in the same constant: per instance as the horizon grows, and unconditionally as the prior becomes diffuse. For arbitrary distortions it stays competitive with the optimal weights, at a ratio governed by a geometric incoherence the algorithm can measure. On real scans split into sites with their own miscalibrated detectors it attains the oracle excess risk; on a companion federation that pulls bias and noise apart, weighting by noise variance is worse than not weighting at all, and CROWD is not. 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/2610.04671 — 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 2026-10-06T05:27:05.977Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).