Metraipolis › archive › dc_f78ff51b99fb

Linesearch-Free Nonlinearly Preconditioned GD with Semiautomatic Geometry Design — arXiv:2609.34288

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.34288
License (as archived)
CC0-1.0
Archived
2026-10-07T23:06:42.519Z
SHA-256 of the archived text
bfa7bc12127c6f315dacdf01d0577f62526d037e5e6a615e35b3771724765cd6
Stable URL of this page
https://metraipolis.com/documento/dc_f78ff51b99fb

How to cite

Linesearch-Free Nonlinearly Preconditioned GD with Semiautomatic Geometry Design — arXiv:2609.34288 — arXiv (en), https://arxiv.org/abs/2609.34288 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f78ff51b99fb (Metraipolis archive dc_f78ff51b99fb, sha256 bfa7bc12127c6f315dacdf01d0577f62526d037e5e6a615e35b3771724765cd6)
BibTeX
@misc{dcf78ff51b99fb,
  title = {Linesearch-Free Nonlinearly Preconditioned GD with Semiautomatic Geometry Design — arXiv:2609.34288},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.34288},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f78ff51b99fb; sha256 bfa7bc12127c6f315dacdf01d0577f62526d037e5e6a615e35b3771724765cd6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34288. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Nonlinear preconditioning makes it possible to adapt gradient updates to the growth of the objective's curvature, but combining its design with suitable stepsize selection is challenging. We propose adaptive dual preconditioned gradient descent (adaptive DPGD), which combines curvature-based preconditioner design with a linesearch-free stepsize rule based on local information. For convex objectives, we establish linear convergence under local strong convexity of the objective. By adapting the stepsize rule, we extend the method to weakly convex objectives and establish asymptotic stationarity without global Lipschitz smoothness. Moreover, our local assumptions give greater freedom in preconditioner design. We exploit this freedom to develop a semiautomatic recipe guided by the objective's curvature, yielding a family of preconditioners that includes those underlying normalized and hyperbolic gradient descent. Experiments on convex and weakly convex problems with real data demonstrate the effectiveness of the preconditioner design and adaptive stepsize selection.

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/2609.34288 — 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 2026-10-07T22:42:39.252Z 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).