Metraipolis › archive › dc_ebbd2bcf9055

Decentralized Sparse Quantile Regression — arXiv:2611.04612

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.04612
License (as archived): CC0-1.0
Archived: 2026-11-04T21:54:47.988Z
SHA-256 of the archived text: 6058a3828bb528147346f7041911db03050a5883d7ffd6c92bd96f4d7ddd5797
Stable URL of this page: https://metraipolis.com/documento/dc_ebbd2bcf9055

How to cite

Decentralized Sparse Quantile Regression — arXiv:2611.04612 — arXiv (en), https://arxiv.org/abs/2611.04612 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ebbd2bcf9055 (Metraipolis archive dc_ebbd2bcf9055, sha256 6058a3828bb528147346f7041911db03050a5883d7ffd6c92bd96f4d7ddd5797)

BibTeX

@misc{dcebbd2bcf9055,
  title = {Decentralized Sparse Quantile Regression — arXiv:2611.04612},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.04612},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ebbd2bcf9055; sha256 6058a3828bb528147346f7041911db03050a5883d7ffd6c92bd96f4d7ddd5797},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04612. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Distributed statistical learning has recently attracted significant attention owing to its computational efficiency and scalability in large-scale systems. However, the non-smooth quantile loss poses substantial challenges to the development of efficient decentralized algorithms for quantile regression. Existing methods may either suffer from slow convergence or rely on smoothing-based approximations that require additional stringent assumptions, particularly in high-dimensional settings. To address these issues, we propose a decentralized framework that integrates gradient tracking with iterative hard thresholding for sparse quantile estimation. The proposed method avoids smoothing approximations and relaxes the initialization requirement. Theoretically, we show that the proposed algorithm achieves linear convergence under stated regularity conditions and that the resulting estimator attains the same order of statistical accuracy as its centralized counterpart. We further develop a decentralized information criterion for selecting the working sparsity level and establish support screening guarantees. Numerical experiments and a real-data study illustrate the finite-sample performance of the proposed method.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv stat.ME, nuovi lavori del giorno).
Categorie arXiv: Methodology (stat.ME) ; Statistics Theory (math.ST); Computation (stat.CO).
Pagina del lavoro: https://arxiv.org/abs/2611.04612 — 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 2026-11-04T21:39:49.515Z dalla pagina https://arxiv.org/list/stat.ME/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).