Metraipolis › archive › dc_31cb1fe83d39

Learning Variable Metrics for Convergent Proximal Splitting Algorithms — arXiv:2610.22204

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.22204
License (as archived)
CC0-1.0
Archived
2026-10-16T10:56:22.543Z
SHA-256 of the archived text
f47d964467a9dab2e5710cbb99c6b289a9d2d0c1c9d367eaa437e787b67d786c
Stable URL of this page
https://metraipolis.com/documento/dc_31cb1fe83d39

How to cite

Learning Variable Metrics for Convergent Proximal Splitting Algorithms — arXiv:2610.22204 — arXiv (en), https://arxiv.org/abs/2610.22204 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_31cb1fe83d39 (Metraipolis archive dc_31cb1fe83d39, sha256 f47d964467a9dab2e5710cbb99c6b289a9d2d0c1c9d367eaa437e787b67d786c)
BibTeX
@misc{dc31cb1fe83d39,
  title = {Learning Variable Metrics for Convergent Proximal Splitting Algorithms — arXiv:2610.22204},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.22204},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_31cb1fe83d39; sha256 f47d964467a9dab2e5710cbb99c6b289a9d2d0c1c9d367eaa437e787b67d786c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.22204. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We propose learned variable metric (LVM), a framework that learns metrics of proximal splitting algorithms adapted to each problem instance, coordinate, and iteration with a convergence guarantee. Proximal splitting algorithms can solve a wide variety of convex optimization problems but often require many iterations to converge. Choosing a suitable metric is an effective remedy, and variable metric theory naturally extends convergence guarantees to metrics that vary over the iterations. Learning is a promising way to design such adaptive metrics beyond the reach of manual design, but a naive implementation leads to (i) an expensive evaluation of a network at every iteration and (ii) difficulty in satisfying the conditions that the theory imposes on the whole infinite sequence of metrics. To resolve these difficulties, we first train a neural network to generate a few representative metrics once per problem instance, and then obtain the metric of every iteration by combining them with basis functions of the normalized iteration index. We present LVM for the proximal gradient method with a quadratic term and the primal-dual hybrid gradient method, and prove their convergence under a mild spectral condition, which is ensured by a rescaling of the representative metrics. In experiments on deblurring and inpainting, LVM reduces the number of iterations to reach a target accuracy in most tested settings compared with several baselines, and the computation time at high accuracies.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv eess.IV, nuovi lavori del giorno).
Categorie arXiv: Image and Video Processing (eess.IV).
Pagina del lavoro: https://arxiv.org/abs/2610.22204 — 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 2026-10-16T09:02:37.213Z dalla pagina https://arxiv.org/list/eess.IV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).