Abstract:Optimization over the intersection of two manifolds arises in a broad range of applications, but is hindered by the coupled geometry of the feasible region. In this paper, we prove that the regularities -- clean intersection and intrinsic transversality -- are equivalent, which yields a tractable projection onto the tangent space of the intersection. Therefore, we propose a geometric method that employs a retraction on only one manifold and updates the iterate along two orthogonal directions. Specifically, the iterates stay on one manifold, and the two directions are responsible for asymptotically approaching the other manifold and decreasing the objective function, respectively. Under intrinsic transversality, we derive the convergence rate for both the feasibility and optimality measures, and show that every accumulation point is first-order stationary. Numerical experiments on problems stemming from sparse and low-rank optimization, including fitting spherical data, approximating hyperbolic embeddings on real data, and computing compressed modes, demonstrate the effectiveness of the proposed method.
| Comments: | 26 pages, 5 figures, 3 tables |
| Subjects: | Optimization and Control (math.OC); Machine Learning (cs.LG); Differential Geometry (math.DG); Numerical Analysis (math.NA) |
| MSC classes: | 65K05, 90C30, 90C46 |
| Cite as: | arXiv:2605.22736 [math.OC] |
| (or arXiv:2605.22736v1 [math.OC] for this version) | |
| https://doi.org/10.48550/arXiv.2605.22736 arXiv-issued DOI via DataCite (pending registration) |
From: Bin Gao [view email]
[v1]
Thu, 21 May 2026 17:08:00 UTC (568 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。