Metraipolis › archive › dc_53bf339a442f

Convergence Guarantees for the Broximal Point Method under Perturbations — arXiv:2611.01933

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.01933
License (as archived)
CC0-1.0
Archived
2026-11-03T18:45:32.556Z
SHA-256 of the archived text
6e0d233a773d42216d808f46ccc0e68440a21607e926a74e93d8e24a390f548b
Stable URL of this page
https://metraipolis.com/documento/dc_53bf339a442f

How to cite

Convergence Guarantees for the Broximal Point Method under Perturbations — arXiv:2611.01933 — arXiv (en), https://arxiv.org/abs/2611.01933 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_53bf339a442f (Metraipolis archive dc_53bf339a442f, sha256 6e0d233a773d42216d808f46ccc0e68440a21607e926a74e93d8e24a390f548b)
BibTeX
@misc{dc53bf339a442f,
  title = {Convergence Guarantees for the Broximal Point Method under Perturbations — arXiv:2611.01933},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.01933},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_53bf339a442f; sha256 6e0d233a773d42216d808f46ccc0e68440a21607e926a74e93d8e24a390f548b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01933. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The Broximal Point Method (BPM) of Gruntkowska et al. (2025) comes with strong guarantees for convex optimization: under convexity alone, it terminates after finitely many steps and converges linearly in function value, with bounds that do not depend on the condition number or on any other regularity property of the objective. Each iteration, however, requires the exact minimization of the objective over a ball, which is generally intractable. As a first step toward implementable variants, we study the method when these subproblems are solved only approximately. We introduce and analyze Inexact BPM, which replaces the exact broximal point by an approximation and makes no assumption on how this approximation is obtained. Under summable or sufficiently small errors, we bound the number of iterations needed to reach a neighborhood of the set of minimizers, and these bounds remain independent of the regularity of the objective. Under the weaker requirement that the errors stay below the ball radius, we prove sublinear convergence in function value for the exact broximal points underlying the perturbed iterates, valid until the target neighborhood is reached, and we recover linear rates under bounded sublevel sets or strong convexity.

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/2611.01933 — 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 2026-11-03T18:14:37.772Z dalla pagina https://arxiv.org/list/math.OC/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).