Metraipolis › archive › dc_f07c381d79a4

Matching the Lower Bounds: Stochastic Contracting Cubic Newton and Its Optimal Acceleration — arXiv:2610.11693

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.11693
License (as archived)
CC0-1.0
Archived
2026-10-09T06:28:04.106Z
SHA-256 of the archived text
f52d33d3adc363c71287bfc25f54489999879e7e2ba24e1fc6a7fca04d3e46c8
Stable URL of this page
https://metraipolis.com/documento/dc_f07c381d79a4

How to cite

Matching the Lower Bounds: Stochastic Contracting Cubic Newton and Its Optimal Acceleration — arXiv:2610.11693 — arXiv (en), https://arxiv.org/abs/2610.11693 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f07c381d79a4 (Metraipolis archive dc_f07c381d79a4, sha256 f52d33d3adc363c71287bfc25f54489999879e7e2ba24e1fc6a7fca04d3e46c8)
BibTeX
@misc{dcf07c381d79a4,
  title = {Matching the Lower Bounds: Stochastic Contracting Cubic Newton and Its Optimal Acceleration — arXiv:2610.11693},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.11693},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f07c381d79a4; sha256 f52d33d3adc363c71287bfc25f54489999879e7e2ba24e1fc6a7fca04d3e46c8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.11693. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We study second-order methods for convex stochastic optimization, where gradients and Hessians are available only through stochastic estimates with variances $\sigma_1^2$ and $\sigma_2^2$, respectively. First, we propose the Stochastic Contracting Cubic Newton method. At each iteration, it minimizes a cubic model with additional quadratic regularization and then contracts the step toward the current point. After $T$ iterations, the method achieves the expected convergence rate $\mathcal{O}(\sigma_1/\sqrt{T}+\sigma_2/T+1/T^2)$. Building on this construction, we develop an accelerated variant achieving $\mathcal{O}(\sigma_1/\sqrt{T}+\sigma_2/T^2+1/T^{7/2})$, matching the known lower bounds of Agafonov et al. (2024) in all three terms.

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/2610.11693 — 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 2026-10-09T05:52:31.602Z dalla pagina https://arxiv.org/list/math.OC/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).