Metraipolis › archive › dc_57694bb5e848

Infeasible Momentum Orthogonalized Methods for Optimization on the Stiefel Manifold — arXiv:2610.41406

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.41406
License (as archived)
CC0-1.0
Archived
2026-11-02T04:57:25.799Z
SHA-256 of the archived text
a085a84d7d7df3235826efbd7e7054d37597d4c729ac8b32509a90086a8ed01f
Stable URL of this page
https://metraipolis.com/documento/dc_57694bb5e848

How to cite

Infeasible Momentum Orthogonalized Methods for Optimization on the Stiefel Manifold — arXiv:2610.41406 — arXiv (en), https://arxiv.org/abs/2610.41406 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_57694bb5e848 (Metraipolis archive dc_57694bb5e848, sha256 a085a84d7d7df3235826efbd7e7054d37597d4c729ac8b32509a90086a8ed01f)
BibTeX
@misc{dc57694bb5e848,
  title = {Infeasible Momentum Orthogonalized Methods for Optimization on the Stiefel Manifold — arXiv:2610.41406},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41406},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_57694bb5e848; sha256 a085a84d7d7df3235826efbd7e7054d37597d4c729ac8b32509a90086a8ed01f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41406. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We study deterministic and stochastic optimization over the Stiefel manifold, explicitly allowing iterates to deviate from the manifold rather than enforcing feasibility via retraction at each step. We introduce Landom, a Landing-type method that constructs momentum in the relative-gradient direction, maps this update to its compact polar factor, and combines the resulting tangential step with a step along the negative gradient of the orthogonality penalty to improve feasibility. Under operator-to-nuclear smoothness, Landom achieves an $O(T^{-1/2})$ bound on the averaged nuclear norm of the relative gradient with exact gradients, and an $O(T^{-1/4})$ bound in expectation with stochastic momentum, bounded variance, and a fixed batch size. Our analysis also provides explicit pathwise bounds on the orthogonality residual, including its dependence on the step size and initial infeasibility. To address the coupling between objective and feasibility correction in Landom, we further propose Landom+, a two-timescale variant in which the tangential and normal step sizes are decoupled. By keeping the normal step size fixed, Landom+ achieves tighter control over the orthogonality residual following an initial transient while maintaining the respective convergence rates for stationarity. Numerical experiments across a range of applications illustrate that the proposed algorithms remain competitive with established manifold optimization approaches.

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/2610.41406 — 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 2026-11-02T04:46:57.667Z dalla pagina https://arxiv.org/list/math.OC/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).