Metraipolis › archive › dc_0f607e43bf42
Curvature, Scaling, and Complexity in Riemannian Projection-Free Optimization — arXiv:2610.05272
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.05272
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T13:05:55.745Z
- SHA-256 of the archived text
2594eff7423d64cd87769240e7b6970b28ff38b9190f68fc9cef8510b879c358- Stable URL of this page
https://metraipolis.com/documento/dc_0f607e43bf42
How to cite
Curvature, Scaling, and Complexity in Riemannian Projection-Free Optimization — arXiv:2610.05272 — arXiv (en), https://arxiv.org/abs/2610.05272 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0f607e43bf42 (Metraipolis archive dc_0f607e43bf42, sha256 2594eff7423d64cd87769240e7b6970b28ff38b9190f68fc9cef8510b879c358)
BibTeX
@misc{dc0f607e43bf42,
title = {Curvature, Scaling, and Complexity in Riemannian Projection-Free Optimization — arXiv:2610.05272},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.05272},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0f607e43bf42; sha256 2594eff7423d64cd87769240e7b6970b28ff38b9190f68fc9cef8510b879c358},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.05272. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Projection-free methods replace projections by linear minimization oracles, making their convergence fundamentally sensitive to the geometry of the feasible region. We develop a geometric framework for this dependence in Riemannian Frank--Wolfe optimization. A power-type double-geodesic modulus quantifies the intrinsic geometry of the feasible set, and an exact transfer principle shows that this modulus induces a Frank--Wolfe scaling margin modulated by the differential of the Riemannian logarithm map. The resulting factorization separates the contributions of feasible-set geometry and ambient Riemannian distortion. Rauch comparison provides explicit curvature-dependent certificates for this distortion, while on the positive-definite cone equipped with the affine-invariant metric the logarithm differential admits an exact spectral characterization in terms of relative eigenvalue spread. Combined with a quadratic error bound, the power-type geometry yields the convergence rate $O(t^{-p/(p-1)})$ for the gap-feedback short-step policy. For every fixed $p>3$, a compact feasible set in a hyperbolic plane attains the matching rate $\Theta(t^{-p/(p-1)})$ under the same policy. The geometry-derived exponent $p/(p-1)$ is therefore sharp for the gap-feedback short-step policy over the geometry-controlled class considered here.
Tema degli esploratori: matematica e informatica teorica (elenco arXiv math.OC, nuovi lavori del giorno).
Categorie arXiv: Optimization and Control (math.OC) ; Differential Geometry (math.DG).
Pagina del lavoro: https://arxiv.org/abs/2610.05272 — 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 2026-10-06T11:21:31.905Z dalla pagina https://arxiv.org/list/math.OC/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).