Metraipolis › archive › dc_ab1d2bf08136

Optimal Byzantine-resilient Federated Learning with User-level Differential Privacy — arXiv:2611.10898

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.10898
License (as archived)
CC0-1.0
Archived
2026-11-10T18:45:56.526Z
SHA-256 of the archived text
6948988b2f0780f64f01a373768b66d20773dff9e8a14f4986bed08d5a3b43a9
Stable URL of this page
https://metraipolis.com/documento/dc_ab1d2bf08136

How to cite

Optimal Byzantine-resilient Federated Learning with User-level Differential Privacy — arXiv:2611.10898 — arXiv (en), https://arxiv.org/abs/2611.10898 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ab1d2bf08136 (Metraipolis archive dc_ab1d2bf08136, sha256 6948988b2f0780f64f01a373768b66d20773dff9e8a14f4986bed08d5a3b43a9)
BibTeX
@misc{dcab1d2bf08136,
  title = {Optimal Byzantine-resilient Federated Learning with User-level Differential Privacy — arXiv:2611.10898},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.10898},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ab1d2bf08136; sha256 6948988b2f0780f64f01a373768b66d20773dff9e8a14f4986bed08d5a3b43a9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.10898. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Real-world deployment of federated learning (FL) requires resilience against adversarial clients and data privacy. Byzantine fault captures the worst-case behavior of adversarial clients, while differential privacy (DP) provides statistical guarantees against privacy loss. In particular, user-level DP guards a client's entire contribution and provides more realistic protection against information leakage. Despite intensive efforts, the minimax-optimal convergence bound of Byzantine-resilient FL with user-level DP remains open. We establish an information-theoretic lower bound for any Byzantine-resilient empirical risk minimization problem under user-level DP and heterogeneous clients. We propose ByzULDP, a central DP algorithm featuring a two-level momentum across the client and server. Client-side momentum mitigates stochastic gradient variance during robust aggregation. Unlike the fault-free case, naively combining non-linear Byzantine-resilient aggregation with central DP noise can be insufficient to guarantee convergence to a bounded neighborhood of a stationary point. Our key contribution is a server-side momentum that leverages a property specific to user-level DP, where privacy sensitivity depends on how client updates are constructed, to empower convergence. ByzULDP achieves the order-optimal convergence bound for strongly-convex objectives, with vanishing error terms decaying at the optimal $O(1/T)$ and $O(1/\sqrt{T})$ rates for strongly-convex and non-convex objectives, respectively. We corroborate our analysis with numerical experiments on real-world datasets across diverse privacy budgets.

Tema degli esploratori: calcolo e infrastrutture (elenco arXiv cs.DC, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Distributed, Parallel, and Cluster Computing (cs.DC); Optimization and Control (math.OC).
Pagina del lavoro: https://arxiv.org/abs/2611.10898 — 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 2026-11-10T18:38:07.451Z dalla pagina https://arxiv.org/list/cs.DC/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).