Metraipolis › archive › dc_bf28368d565a

Wasserstein accelerated proximal gradient algorithms — arXiv:2611.03524

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.03524
License (as archived)
CC0-1.0
Archived
2026-11-03T11:32:35.052Z
SHA-256 of the archived text
023c1592fc1303bec8b670e97ba1b5d68e37e8cd2f909f36300e55727637986d
Stable URL of this page
https://metraipolis.com/documento/dc_bf28368d565a

How to cite

Wasserstein accelerated proximal gradient algorithms — arXiv:2611.03524 — arXiv (en), https://arxiv.org/abs/2611.03524 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bf28368d565a (Metraipolis archive dc_bf28368d565a, sha256 023c1592fc1303bec8b670e97ba1b5d68e37e8cd2f909f36300e55727637986d)
BibTeX
@misc{dcbf28368d565a,
  title = {Wasserstein accelerated proximal gradient algorithms — arXiv:2611.03524},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.03524},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bf28368d565a; sha256 023c1592fc1303bec8b670e97ba1b5d68e37e8cd2f909f36300e55727637986d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.03524. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We propose accelerated proximal gradient methods for composite optimization problems on the quadratic Wasserstein space of probability measures, including Kullback--Leibler divergence minimization. The objective function consists of a smooth geodesically convex functional and a possibly nonsmooth regularizer that is convex along generalized geodesics. The convexity and smoothness conditions on the smooth component are imposed only on the feasible set. As a preliminary result, we establish the equivalence between geodesic convexity of the smooth functional on the feasible set and convexity of its Hilbert-space lift on the corresponding feasible set. Assuming exact proximal steps, we prove an $O(k^{-2})$ convergence rate for the objective gap when the smooth component is geodesically convex and accelerated linear convergence when it is geodesically strongly convex. We also describe particle approximations of these algorithms.

Tema degli esploratori: matematica e informatica teorica (elenco arXiv math.OC, nuovi lavori del giorno).
Categorie arXiv: Optimization and Control (math.OC).
Pagina del lavoro: https://arxiv.org/abs/2611.03524 — 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 2026-11-03T11:04:22.287Z dalla pagina https://arxiv.org/list/math.OC/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).