Metraipolis › archive › dc_4747659e7ade
A Linearly Convergent Projection-Free Algorithm for Smooth Convex Sets — arXiv:2608.04321
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.04321
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T11:38:25.989Z
- SHA-256 of the archived text
9f41c554d9ca18fec3b3bcf6dc9e17ff6c69ffed4262642306fb32f441ae0f8f- Stable URL of this page
https://metraipolis.com/documento/dc_4747659e7ade
How to cite
A Linearly Convergent Projection-Free Algorithm for Smooth Convex Sets — arXiv:2608.04321 — arXiv (en), https://arxiv.org/abs/2608.04321 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4747659e7ade (Metraipolis archive dc_4747659e7ade, sha256 9f41c554d9ca18fec3b3bcf6dc9e17ff6c69ffed4262642306fb32f441ae0f8f)
BibTeX
@misc{dc4747659e7ade,
title = {A Linearly Convergent Projection-Free Algorithm for Smooth Convex Sets — arXiv:2608.04321},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.04321},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4747659e7ade; sha256 9f41c554d9ca18fec3b3bcf6dc9e17ff6c69ffed4262642306fb32f441ae0f8f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.04321. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We consider minimizing a smooth, strongly convex function over a convex set. Projected gradient descent is known to converge linearly in this setting, but each iteration requires a projection onto the feasible set, which may be computationally expensive. We show that when the feasible set is smooth, projection can be replaced by one gradient computation and a single supporting-tangent computation per iteration, while preserving linear convergence. Moreover, the required tangent can be approximated to sufficient accuracy using $\widetilde O(d)$ membership-oracle queries, where $d$ is the ambient dimension. Previously, projection-free linear convergence was known only for polyhedral sets or for sets that are both smooth and strongly convex. Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-08-06 in math.OC). Categorie arXiv: Optimization and Control (math.OC). Pagina del lavoro: https://arxiv.org/abs/2608.04321 — 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 2026-10-31T11:28:34.326Z dalla pagina https://arxiv.org/catchup/math.OC/2026-08-06?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).