Metraipolis › archive › dc_8a1567077baa

Operator Splitting Methods with Online Scaling — arXiv:2609.10732

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.10732
License (as archived)
CC0-1.0
Archived
2026-10-16T06:00:57.184Z
SHA-256 of the archived text
5510d25760fedc5724cb259415d75dad50c417b732cc3cd187eac233989ddcd3
Stable URL of this page
https://metraipolis.com/documento/dc_8a1567077baa

How to cite

Operator Splitting Methods with Online Scaling — arXiv:2609.10732 — arXiv (en), https://arxiv.org/abs/2609.10732 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8a1567077baa (Metraipolis archive dc_8a1567077baa, sha256 5510d25760fedc5724cb259415d75dad50c417b732cc3cd187eac233989ddcd3)
BibTeX
@misc{dc8a1567077baa,
  title = {Operator Splitting Methods with Online Scaling — arXiv:2609.10732},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.10732},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8a1567077baa; sha256 5510d25760fedc5724cb259415d75dad50c417b732cc3cd187eac233989ddcd3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.10732. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

This paper develops a principled framework for automatically tuning preconditioners in operator splitting methods, including forward-backward splitting, Douglas-Rachford splitting, and the alternating direction method of multipliers. We interpret these splitting methods as preconditioned gradient descent applied to their corresponding envelope functions and use online learning to adaptively learn the preconditioner during optimization. Our framework achieves asymptotically faster convergence rates and accelerates the solution of important optimization problems, including Lasso, $\ell_1$-regularized logistic regression, and quadratic programming. Extensive numerical experiments validate our theoretical results and demonstrate the practical effectiveness of the proposed approach.

Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-09-11 in math.OC).
Categorie arXiv: Optimization and Control (math.OC).
Pagina del lavoro: https://arxiv.org/abs/2609.10732 — 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 2026-10-16T05:52:41.392Z dalla pagina https://arxiv.org/catchup/math.OC/2026-09-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).