Metraipolis › archive › dc_d65711e02df0
Silver Rate Is (Almost) Optimal for Gradient Descent — arXiv:2609.09152
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.09152
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T14:02:35.689Z
- SHA-256 of the archived text
162e65931589b4904071ef3ce39e23ad9b98a4ec099642041bb814bb6a3f1ab5- Stable URL of this page
https://metraipolis.com/documento/dc_d65711e02df0
How to cite
Silver Rate Is (Almost) Optimal for Gradient Descent — arXiv:2609.09152 — arXiv (en), https://arxiv.org/abs/2609.09152 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d65711e02df0 (Metraipolis archive dc_d65711e02df0, sha256 162e65931589b4904071ef3ce39e23ad9b98a4ec099642041bb814bb6a3f1ab5)
BibTeX
@misc{dcd65711e02df0,
title = {Silver Rate Is (Almost) Optimal for Gradient Descent — arXiv:2609.09152},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.09152},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d65711e02df0; sha256 162e65931589b4904071ef3ce39e23ad9b98a4ec099642041bb814bb6a3f1ab5},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.09152. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We study how far gradient descent (GD) can be accelerated by predetermined stepsizes in smooth convex optimization. Writing $p_{\mathrm{sil}}=\log_2(1+\sqrt{2})$, we prove an $\Omega\left(n^{-p_{\mathrm{sil}}-O(\sqrt{\log\log n/\log n})}\right)$ non-anytime lower bound. In the anytime setting, every infinite schedule has infinitely many horizons with error $\Omega\left(n^{-\frac{2p_{\mathrm{sil}}}{1+p_{\mathrm{sil}}}-O(\sqrt{\log\log n/\log n})}\right)$. Together with the silver-schedule upper bound [Altschuler and Parrilo, 2025] and the anytime upper bound [Zhang et al., 2025], our results determine the optimal polynomial convergence exponents in both settings.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.LG).
Categorie arXiv: Optimization and Control (math.OC) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.09152 — 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 2026-10-16T13:39:43.308Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).