Metraipolis › archive › dc_fdb1607fdf1c
Near-Optimal Convex Optimization with Lazy Second-Order Oracles — arXiv:2610.03222
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.03222
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-05T23:10:49.623Z
- SHA-256 of the archived text
209b25a6299f387b2b9859bbc6ea195ad3f76c22b09b2158babedd820e7c5897- Stable URL of this page
https://metraipolis.com/documento/dc_fdb1607fdf1c
How to cite
Near-Optimal Convex Optimization with Lazy Second-Order Oracles — arXiv:2610.03222 — arXiv, https://arxiv.org/abs/2610.03222 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fdb1607fdf1c (Metraipolis archive dc_fdb1607fdf1c, sha256 209b25a6299f387b2b9859bbc6ea195ad3f76c22b09b2158babedd820e7c5897)
BibTeX
@misc{dcfdb1607fdf1c,
title = {Near-Optimal Convex Optimization with Lazy Second-Order Oracles — arXiv:2610.03222},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.03222},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fdb1607fdf1c; sha256 209b25a6299f387b2b9859bbc6ea195ad3f76c22b09b2158babedd820e7c5897},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.03222. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
This paper studies the complexity of convex optimization using lazy second-order oracles (Doikov, Chayti, and Jaggi, ICML 2023), where an algorithm queries gradients every iteration and Hessians once per $m$ iterations. Under this setting, we show a lower bound of $\Omega(m+ m^{1/7} \epsilon^{-2/7})$ on the number of total iterations to find an $\epsilon$-solution using a novel block zero-chain construction. Then we propose a novel method that achieves a new upper bound of $\tilde{\mathcal{O}}(m+ m^{1/7} \epsilon^{-2/7})$, which significantly improves the prior one (Chen, Liu, Luo, and Zhang, COLT 2026) of $\tilde{\mathcal{O}}(m+ m^{13/21} \epsilon^{-2/7})$ and is tight up to logarithmic factors.
Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Optimization and Control (math.OC) ; Machine Learning (cs.LG); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2610.03222 — 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 2026-10-05T23:01:38.767Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).