Metraipolis › archive › dc_8ab914f4f87f

A counterexample to a three-step convergence bound for BFGS with exact line search — arXiv:2611.02719

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.02719
License (as archived)
CC0-1.0
Archived
2026-11-03T18:45:40.188Z
SHA-256 of the archived text
b99c14f1ffe8fe352ac6613ed22af2e96b9cd0821936646a49745d7bdeb7ca70
Stable URL of this page
https://metraipolis.com/documento/dc_8ab914f4f87f

How to cite

A counterexample to a three-step convergence bound for BFGS with exact line search — arXiv:2611.02719 — arXiv (en), https://arxiv.org/abs/2611.02719 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8ab914f4f87f (Metraipolis archive dc_8ab914f4f87f, sha256 b99c14f1ffe8fe352ac6613ed22af2e96b9cd0821936646a49745d7bdeb7ca70)
BibTeX
@misc{dc8ab914f4f87f,
  title = {A counterexample to a three-step convergence bound for BFGS with exact line search — arXiv:2611.02719},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.02719},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8ab914f4f87f; sha256 b99c14f1ffe8fe352ac6613ed22af2e96b9cd0821936646a49745d7bdeb7ca70},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02719. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We disprove a three-step error estimate for the Broyden--Fletcher--Goldfarb--Shanno {(BFGS)} method with exact line searches. We construct a globally strongly convex function $F\in C^\infty(\mathbb R^3)$ and a single nonterminating trajectory $x_k\to0$ for which $\limsup_{k\to\infty}\|x_{k+3}\|/(\|x_{k+2}\|\|x_k\|)=+\infty$. The Hessian of $F$ lies between $\tfrac12 I$ and $\tfrac32 I$ everywhere, and $F(x)-\tfrac12\|x\|^2$ is compactly supported with all derivatives vanishing at $0$. The proof first constructs point-gradient pairs satisfying the exact BFGS step identities. A five-step cycle produces a large three-step quotient and restores an invariant plane for the actual updated matrix, allowing the cycle to be repeated with arbitrarily small gradient errors. Disjoint smooth corrections to a quadratic then realize all the pairs by one objective. Strong convexity identifies the prescribed points with the unique exact line-search minimizers. Thus smoothness and strong convexity do not imply the proposed product estimate, even for an objective that agrees with a quadratic to every order at its minimizer.

Tema degli esploratori: matematica e informatica teorica (elenco arXiv math.OC, nuovi lavori del giorno).
Categorie arXiv: Optimization and Control (math.OC).
Pagina del lavoro: https://arxiv.org/abs/2611.02719 — 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 2026-11-03T18:14:37.788Z dalla pagina https://arxiv.org/list/math.OC/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).