Metraipolis › archive › dc_77d0ff2e5fb0

Primal Acceleration of Newton's Method — arXiv:2608.21359

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.21359
License (as archived)
CC0-1.0
Archived
2026-10-18T10:31:41.546Z
SHA-256 of the archived text
dcb5aaeca43d447befbf4a4a61ce3e1ff9d14d3adc266b88888d6c5337ef2b4b
Stable URL of this page
https://metraipolis.com/documento/dc_77d0ff2e5fb0

How to cite

Primal Acceleration of Newton's Method — arXiv:2608.21359 — arXiv (en), https://arxiv.org/abs/2608.21359 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_77d0ff2e5fb0 (Metraipolis archive dc_77d0ff2e5fb0, sha256 dcb5aaeca43d447befbf4a4a61ce3e1ff9d14d3adc266b88888d6c5337ef2b4b)
BibTeX
@misc{dc77d0ff2e5fb0,
  title = {Primal Acceleration of Newton's Method — arXiv:2608.21359},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.21359},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_77d0ff2e5fb0; sha256 dcb5aaeca43d447befbf4a4a61ce3e1ff9d14d3adc266b88888d6c5337ef2b4b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.21359. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We develop a new direct accelerated Newton method for minimizing convex functions with Lipschitz continuous Hessian. The algorithm uses only primal variables and performs just one linear solve per iteration. With a simple predetermined choice of parameters, it achieves the global convergence rate of $O(1/k^3)$ in terms of the functional residual. To the best of our knowledge, this is the first second-order method for this problem class attaining this rate while relying solely on one linear system solve per iteration (without solving auxiliary nonlinear regularized subproblems, such as cubic regularization, performing nonlinear parameter searches, or using dual extragradient corrections). Our method can be implemented in a Hessian-free way, using an inexact linear system solver, while preserving the fast global rate. We further extend our construction to arbitrary geometry through Bregman divergence, and to composite optimization problems.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-24 in cs.LG).
Categorie arXiv: Optimization and Control (math.OC) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.21359 — 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 2026-10-18T10:27:56.014Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).