Metraipolis › archive › dc_8563d94eceba

Byzantine-Robust Distributed Sparse Softmax Regression — arXiv:2611.09110

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.09110
License (as archived): CC0-1.0
Archived: 2026-11-09T22:42:42.623Z
SHA-256 of the archived text: 2ca44759b7af75a658334a20f46da2fa70f59b5c9536e8f4b592503b1d526552
Stable URL of this page: https://metraipolis.com/documento/dc_8563d94eceba

How to cite

Byzantine-Robust Distributed Sparse Softmax Regression — arXiv:2611.09110 — arXiv (en), https://arxiv.org/abs/2611.09110 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8563d94eceba (Metraipolis archive dc_8563d94eceba, sha256 2ca44759b7af75a658334a20f46da2fa70f59b5c9536e8f4b592503b1d526552)

BibTeX

@misc{dc8563d94eceba,
  title = {Byzantine-Robust Distributed Sparse Softmax Regression — arXiv:2611.09110},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.09110},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8563d94eceba; sha256 2ca44759b7af75a658334a20f46da2fa70f59b5c9536e8f4b592503b1d526552},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.09110. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We study Byzantine-robust distributed sparse softmax regression in high-dimensional settings. We propose a communication-efficient distributed algorithm that employs robust aggregation methods---coordinate-wise trimmed mean and coordinate-wise median---to defend against Byzantine attacks. Under sub-Gaussian design assumptions with sparsity constraints, we establish that the distributed estimator achieves the convergence rate of $O_{P}(K^{\frac{5}{2}}\sqrt{s\log(Kd)/N})$ when the Byzantine fraction $\alpha \asymp 1/\sqrt{m}$, matching the centralized oracle rate. Numerical experiments on synthetic data demonstrate the superior performance of the proposed method.

Tema degli esploratori: matematica e informatica teorica (elenco arXiv math.ST, nuovi lavori del giorno).
Categorie arXiv: Statistics Theory (math.ST).
Pagina del lavoro: https://arxiv.org/abs/2611.09110 — 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 2026-11-09T22:35:47.239Z dalla pagina https://arxiv.org/list/math.ST/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).