Metraipolis › archive › dc_e642d3ca3880
Improved Gradient Descent Lower Bounds Beyond Nesterov — arXiv:2609.02855
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.02855
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T05:01:42.930Z
- SHA-256 of the archived text
7e3e639a3d2313e5972f3c3e7d4e7bd6b637a827371daf88400d86f896c35048- Stable URL of this page
https://metraipolis.com/documento/dc_e642d3ca3880
How to cite
Improved Gradient Descent Lower Bounds Beyond Nesterov — arXiv:2609.02855 — arXiv (en), https://arxiv.org/abs/2609.02855 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e642d3ca3880 (Metraipolis archive dc_e642d3ca3880, sha256 7e3e639a3d2313e5972f3c3e7d4e7bd6b637a827371daf88400d86f896c35048)
BibTeX
@misc{dce642d3ca3880,
title = {Improved Gradient Descent Lower Bounds Beyond Nesterov — arXiv:2609.02855},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.02855},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e642d3ca3880; sha256 7e3e639a3d2313e5972f3c3e7d4e7bd6b637a827371daf88400d86f896c35048},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.02855. 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. Going beyond the classical $\Omega(n^{-2})$ first-order oracle lower bound of Nemirovsky and Yudin (1983), we prove an $\Omega(n^{-1.6342})$ non-anytime lower bound and an $\Omega(n^{-1.2408})$ anytime lower bound. These improve the recent $\Omega(n^{-1.932})$ non-anytime lower bound of Ma and Chen (2026) and the $\Omega(n^{-4/3})$ anytime lower bound of Tsai et al. (2026), respectively. Both results continue to hold when the stepsizes may be negative. Our anytime lower bound also shows that the $O(n^{-\log_2(1+\sqrt{2})})$ rate of non-anytime silver schedules (Altschuler and Parrilo, 2025; Grimmer et al., 2025) is unattainable in the anytime setting. This establishes a strict separation between the two settings.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-03 in cs.LG).
Categorie arXiv: Optimization and Control (math.OC) ; Machine Learning (cs.LG); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2609.02855 — 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 2026-10-17T04:09:43.389Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-03?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).