Metraipolis › archive › dc_7d7beecc7f1a
Near-Optimal Second-Order Convex Finite-Sum Optimization under Individual Smoothness — arXiv:2610.42040
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.42040
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T07:33:34.841Z
- SHA-256 of the archived text
26086f35865aa68cfea01dd9c1ca9a20d34671eea43a7cd4d144a9f926ab39aa- Stable URL of this page
https://metraipolis.com/documento/dc_7d7beecc7f1a
How to cite
Near-Optimal Second-Order Convex Finite-Sum Optimization under Individual Smoothness — arXiv:2610.42040 — arXiv (en), https://arxiv.org/abs/2610.42040 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7d7beecc7f1a (Metraipolis archive dc_7d7beecc7f1a, sha256 26086f35865aa68cfea01dd9c1ca9a20d34671eea43a7cd4d144a9f926ab39aa)
BibTeX
@misc{dc7d7beecc7f1a,
title = {Near-Optimal Second-Order Convex Finite-Sum Optimization under Individual Smoothness — arXiv:2610.42040},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.42040},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7d7beecc7f1a; sha256 26086f35865aa68cfea01dd9c1ca9a20d34671eea43a7cd4d144a9f926ab39aa},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.42040. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We study the stochastic second-order oracle complexity of solving smooth convex finite-sum optimization with $n$ components. Very recently, Tsedenov \& Kovalev (2026) showed that the minimax optimal complexity under averaged smoothness and convexity is $\tilde{\Theta}(n + n^{6/7} \epsilon^{-2/7})$ by establishing nearly matching upper and lower bounds. In this paper, we show that individual smoothness and convexity provably enable further acceleration, where the lower complexity bound is $\Omega(n+ n^{5/7} \epsilon^{-2/7})$ under this stronger assumption. Then, by establishing a novel second-order self-bounding inequality, we design a new Taylor-corrected lazy Newton method, which can lead to a better complexity of $\tilde{\mathcal{O}}(n + n^{5/7} \epsilon^{-2/7})$ by applying the optimal Monteiro-Svaiter acceleration, matching our lower bound up to only logarithmic factors.
Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Optimization and Control (math.OC) ; Artificial Intelligence (cs.AI); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2610.42040 — 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 2026-11-03T07:29:33.753Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).