Metraipolis › archive › dc_3451ff9353df

Optimal Parameter-Free Second-order Acceleration with Inexact Hessians under Generalized Smoothness — arXiv:2609.32977

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.32977
License (as archived)
CC0-1.0
Archived
2026-10-07T23:06:33.950Z
SHA-256 of the archived text
e999bcbcc968e649c519bfcdc158c57a437bb972dbf2c6aabc0416d7e9876a3c
Stable URL of this page
https://metraipolis.com/documento/dc_3451ff9353df

How to cite

Optimal Parameter-Free Second-order Acceleration with Inexact Hessians under Generalized Smoothness — arXiv:2609.32977 — arXiv (en), https://arxiv.org/abs/2609.32977 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3451ff9353df (Metraipolis archive dc_3451ff9353df, sha256 e999bcbcc968e649c519bfcdc158c57a437bb972dbf2c6aabc0416d7e9876a3c)
BibTeX
@misc{dc3451ff9353df,
  title = {Optimal Parameter-Free Second-order Acceleration with Inexact Hessians under Generalized Smoothness — arXiv:2609.32977},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.32977},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3451ff9353df; sha256 e999bcbcc968e649c519bfcdc158c57a437bb972dbf2c6aabc0416d7e9876a3c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32977. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We study second-order convex optimization under generalized Hessian smoothness, where the local Hessian Lipschitz constant may grow linearly with the gradient norm. For inexact Hessians, we develop adaptive algorithms, including an accelerated Monteiro-Svaiter-type method whose complexity matches the lower bound for second-order methods with $\delta$-inexact Hessians in the classical Lipschitz-Hessian setting. Our methods are parameter-free in the sense that they require no problem-specific parameters as input, including the Hessian inexactness level $\delta$ and smoothness constants. Instead, their backtracking adapts a single regularization parameter that jointly captures Hessian inexactness and local Hessian smoothness. The resulting rates split into two regimes. Far from the solution, the gradient-dependent smoothness term yields geometric convergence. Near the solution, the rate is governed by the ordinary Hessian smoothness and the inexactness level $\delta$, recovering the classical Lipschitz-Hessian guarantees.

Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-09-29 in math.OC).
Categorie arXiv: Optimization and Control (math.OC).
Pagina del lavoro: https://arxiv.org/abs/2609.32977 — 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 2026-10-07T22:42:39.204Z dalla pagina https://arxiv.org/catchup/math.OC/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).