Metraipolis › archive › dc_a01b3b5ee0ea
Boundary Geometry and Global Rates of Cyclic Coordinate Descent for SVM Duals — arXiv:2609.39240
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.39240
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T14:11:22.792Z
- SHA-256 of the archived text
a7efa8da371c7845accc511bf175f1497a19f58217d8b51a200b87baca94116d- Stable URL of this page
https://metraipolis.com/documento/dc_a01b3b5ee0ea
How to cite
Boundary Geometry and Global Rates of Cyclic Coordinate Descent for SVM Duals — arXiv:2609.39240 — arXiv (en), https://arxiv.org/abs/2609.39240 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a01b3b5ee0ea (Metraipolis archive dc_a01b3b5ee0ea, sha256 a7efa8da371c7845accc511bf175f1497a19f58217d8b51a200b87baca94116d)
BibTeX
@misc{dca01b3b5ee0ea,
title = {Boundary Geometry and Global Rates of Cyclic Coordinate Descent for SVM Duals — arXiv:2609.39240},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.39240},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a01b3b5ee0ea; sha256 a7efa8da371c7845accc511bf175f1497a19f58217d8b51a200b87baca94116d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.39240. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Cyclic coordinate descent is widely used to train support vector machines, but global linear convergence alone gives limited guidance about the rate on a particular instance. We study exact cyclic coordinate minimization for box-constrained convex quadratics and develop global contraction bounds that capture both coordinate order and boundary geometry. Our convergence certificate combines two ingredients: interactions between successive coordinate updates, encoded by the triangular part of the normalized Hessian, and objective growth, captured by a matrix lower bound on the optimality gap. It remains valid for cases with singular Hessians, nonunique minimizers, and updates clipped at the boundary. An error-bound specialization of our analysis strictly sharpens the Wang-Lin factor when both use the same error-bound constant. In the positive-definite case, the analysis shows that the worst-case contraction of one Gauss-Seidel sweep remains a global upper bound under box constraints, with equality for an interior optimizer. We also demonstrate the limitations of Hessian-only bounds by constructing a two-coordinate family with a fixed singular normalized Hessian, whose worst-case contraction approaches one as its boundary margin vanishes. The theory is complemented by practical procedures for bounding the worst-case contraction on individual instances and numerical evaluation on several classical SVM datasets. Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-10-01 in math.OC). Categorie arXiv: Optimization and Control (math.OC). Pagina del lavoro: https://arxiv.org/abs/2609.39240 — 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 2026-10-07T14:03:18.260Z dalla pagina https://arxiv.org/catchup/math.OC/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).