Metraipolis › archive › dc_50e92ec29ec0
A Riemannian Inertial Adaptive Gradient Method with Momentum Restart — arXiv:2609.32997
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.32997
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T23:06:35.241Z
- SHA-256 of the archived text
5599c58d1e02ea0c8831f318bbe4b15e84f4e34fb71748b990a6e0b370031d85- Stable URL of this page
https://metraipolis.com/documento/dc_50e92ec29ec0
How to cite
A Riemannian Inertial Adaptive Gradient Method with Momentum Restart — arXiv:2609.32997 — arXiv (en), https://arxiv.org/abs/2609.32997 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_50e92ec29ec0 (Metraipolis archive dc_50e92ec29ec0, sha256 5599c58d1e02ea0c8831f318bbe4b15e84f4e34fb71748b990a6e0b370031d85)
BibTeX
@misc{dc50e92ec29ec0,
title = {A Riemannian Inertial Adaptive Gradient Method with Momentum Restart — arXiv:2609.32997},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.32997},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_50e92ec29ec0; sha256 5599c58d1e02ea0c8831f318bbe4b15e84f4e34fb71748b990a6e0b370031d85},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32997. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We propose RIAG-R, a Riemannian Inertial Adaptive Gradient method with gradient-triggered Restart, for optimization on Riemannian manifolds. RIAG-R combines three ingredients: an AdaGrad-type adaptive step-size that requires no knowledge of the Lipschitz constant; inertial extrapolation in the tangent space via the exponential map to accelerate convergence; and a restart rule, costing only one extra inner product per iteration, that detects and corrects the momentum-saturation pathology induced by manifold curvature. We establish a per-iteration descent inequality, an optimal $O(\varepsilon^{-2})$-iteration complexity, a convergence result for cluster points of the generated sequence, and a linear convergence rate under the Riemannian Polyak-Łojasiewicz inequality. Numerical experiments on four representative matrix manifold optimization problems including sphere, Stiefel, symmetric positive-definite, and Grassmann manifolds demonstrate that RIAG-R consistently outperforms non-inertial and restart-free inertial baselines, confirming that adaptive restart is essential to realizing the benefits of momentum on curved spaces.
Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-09-29 in math.OC).
Categorie arXiv: Optimization and Control (math.OC).
Pagina del lavoro: https://arxiv.org/abs/2609.32997 — 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 2026-10-07T22:42:39.210Z dalla pagina https://arxiv.org/catchup/math.OC/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).