Metraipolis › archive › dc_f5094226cbfc

Pursuing Optimal Stepsize in Adaptive Gradient-Based Quadratic Optimization — arXiv:2608.03546

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.03546
License (as archived)
CC0-1.0
Archived
2026-10-31T12:48:29.415Z
SHA-256 of the archived text
c3cb9887bbd3fe6d101a241a771a70179ec46baf52337f8a6fa44ce07e218d13
Stable URL of this page
https://metraipolis.com/documento/dc_f5094226cbfc

How to cite

Pursuing Optimal Stepsize in Adaptive Gradient-Based Quadratic Optimization — arXiv:2608.03546 — arXiv (en), https://arxiv.org/abs/2608.03546 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f5094226cbfc (Metraipolis archive dc_f5094226cbfc, sha256 c3cb9887bbd3fe6d101a241a771a70179ec46baf52337f8a6fa44ce07e218d13)
BibTeX
@misc{dcf5094226cbfc,
  title = {Pursuing Optimal Stepsize in Adaptive Gradient-Based Quadratic Optimization — arXiv:2608.03546},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.03546},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f5094226cbfc; sha256 c3cb9887bbd3fe6d101a241a771a70179ec46baf52337f8a6fa44ce07e218d13},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.03546. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In this paper, we address the problem of achieving fast convergence in gradient descent for quadratic functions without relying on a priori knowledge of global function parameters. Inspired by adaptive stepsize algorithms for smooth convex functions, we propose a computationally lightweight strategy based on running estimates of minimal and maximal local curvatures. We prove that our proposed algorithm converges to the optimal constant stepsize which achieves the fastest convergence. Simulations show that the convergence rate achieved by our proposed algorithm is comparable or superior to recent adaptive approaches both in the quadratic case under consideration and in a preliminary test on logistic classification.

Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-08-05 in math.OC).
Categorie arXiv: Optimization and Control (math.OC).
Pagina del lavoro: https://arxiv.org/abs/2608.03546 — 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 2026-10-31T12:35:48.814Z dalla pagina https://arxiv.org/catchup/math.OC/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).