Metraipolis › archive › dc_e362bc0aba0c
Complexity analysis of trust-region methods under $(α,L_0,L_1)$-smoothness — arXiv:2609.33238
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.33238
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T23:06:36.819Z
- SHA-256 of the archived text
9fbacdcea9da185d753f4c260c23581741b6f2007e719057ca2e85c9f2fad456- Stable URL of this page
https://metraipolis.com/documento/dc_e362bc0aba0c
How to cite
Complexity analysis of trust-region methods under $(α,L_0,L_1)$-smoothness — arXiv:2609.33238 — arXiv (en), https://arxiv.org/abs/2609.33238 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e362bc0aba0c (Metraipolis archive dc_e362bc0aba0c, sha256 9fbacdcea9da185d753f4c260c23581741b6f2007e719057ca2e85c9f2fad456)
BibTeX
@misc{dce362bc0aba0c,
title = {Complexity analysis of trust-region methods under $(α,L_0,L_1)$-smoothness — arXiv:2609.33238},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.33238},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e362bc0aba0c; sha256 9fbacdcea9da185d753f4c260c23581741b6f2007e719057ca2e85c9f2fad456},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.33238. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Generalized smoothness assumptions have attracted growing attention in recent years, motivated in part by machine learning problems in which the gradient of the objective function may not be Lipschitz continuous. Among the most prominent of these is the $(\alpha, L_0, L_1)$-smoothness assumption. Existing methods that attain the best known complexity bounds require knowledge of, or upper bounds on, $\alpha$, $L_0$ and $L_1$, while the few parameter-agnostic methods available do not recover those bounds. In this paper, we show that trust-region methods attain the best known bounds for $(\alpha, L_0, L_1)$-smooth objective functions without prior knowledge of these parameters. Establishing these results requires new analytical tools, beyond those used in classical trust-region complexity analyses. We further show that our working model assumption allows the use of general model Hessian approximations and, in particular, accommodates limited-memory quasi-Newton updates. Finally, we show that our complexity bound is sharp in the nonconvex setting. Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-09-29 in math.OC). Categorie arXiv: Optimization and Control (math.OC). Pagina del lavoro: https://arxiv.org/abs/2609.33238 — 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 2026-10-07T22:42:39.221Z dalla pagina https://arxiv.org/catchup/math.OC/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).