Metraipolis › archive › dc_0712a1becc7d
Descent--Ascent Structure of Uniform Nondegeneracy — arXiv:2610.06115
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.06115
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T13:06:24.262Z
- SHA-256 of the archived text
e15c507eae677145be17b09078307fcc338ca27cfa1c2a8d0632f4d670735cd3- Stable URL of this page
https://metraipolis.com/documento/dc_0712a1becc7d
How to cite
Descent--Ascent Structure of Uniform Nondegeneracy — arXiv:2610.06115 — arXiv (en), https://arxiv.org/abs/2610.06115 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0712a1becc7d (Metraipolis archive dc_0712a1becc7d, sha256 e15c507eae677145be17b09078307fcc338ca27cfa1c2a8d0632f4d670735cd3)
BibTeX
@misc{dc0712a1becc7d,
title = {Descent--Ascent Structure of Uniform Nondegeneracy — arXiv:2610.06115},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.06115},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0712a1becc7d; sha256 e15c507eae677145be17b09078307fcc338ca27cfa1c2a8d0632f4d670735cd3},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.06115. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Classical models such as smooth strongly convex minimization and strongly convex--strongly concave optimization combine two types of curvature information: curvature remains uniformly separated from zero, and its positive and negative orientations are prescribed in advance. Uniform nondegeneracy disentangles these roles, retaining the separation from zero while allowing the curvature orientation to vary across the domain. We identify a family of descent--ascent inequalities (DAI) that characterizes uniform nondegeneracy and naturally gives rise to Alternating Descent Ascent (ADA), a simple explicit method that alternates full-gradient descent and ascent. ADA converges globally and linearly to the unique stationary point from arbitrary initialization, with dimension-free first-order complexity. The framework recovers the smooth strongly convex setting as a limit and encompasses the strongly convex--strongly concave and linearly constrained settings, highlighting uniform nondegeneracy as a common first-order structure across various classical regimes. 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/2610.06115 — 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 2026-10-06T11:21:31.918Z dalla pagina https://arxiv.org/list/math.OC/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).