Metraipolis › archive › dc_85b855768a30
On the Complexity of BFGS Method for Smooth Convex Optimization — arXiv:2608.16009
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.16009
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T20:18:47.467Z
- SHA-256 of the archived text
064d6794d34e532b57d4436f6cbf900ffe76fe98870dc5cf4e9f9af4be2f84ce- Stable URL of this page
https://metraipolis.com/documento/dc_85b855768a30
How to cite
On the Complexity of BFGS Method for Smooth Convex Optimization — arXiv:2608.16009 — arXiv (en), https://arxiv.org/abs/2608.16009 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_85b855768a30 (Metraipolis archive dc_85b855768a30, sha256 064d6794d34e532b57d4436f6cbf900ffe76fe98870dc5cf4e9f9af4be2f84ce)
BibTeX
@misc{dc85b855768a30,
title = {On the Complexity of BFGS Method for Smooth Convex Optimization — arXiv:2608.16009},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.16009},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_85b855768a30; sha256 064d6794d34e532b57d4436f6cbf900ffe76fe98870dc5cf4e9f9af4be2f84ce},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16009. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We study the BFGS method with an Armijo-Wolfe line search for minimizing convex functions with Lipschitz-continuous gradients, without assuming strong convexity. We establish a global iteration complexity bound of $\mathcal{O}(k^{-1/2})$ for the smallest gradient norm among the first $k$ iterates. Moreover, when the initial sublevel set is bounded, we show that the function value gap converges at a rate of $\mathcal{O}(k^{-1})$. Our analysis leverages the classical trace-log-determinant potential function and reveals that a key inequality underlying this potential function remains valid without strong convexity.
Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-08-18 in math.OC).
Categorie arXiv: Optimization and Control (math.OC).
Pagina del lavoro: https://arxiv.org/abs/2608.16009 — 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 2026-10-18T19:45:07.847Z dalla pagina https://arxiv.org/catchup/math.OC/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).