研究人员开发了一种用于Stiefel流形的新型二阶优化方法，该方法避免了回缩，为高精度要求提供了更高的效率。该方法结合了切向分量以减小目标函数，以及使用牛顿-舒尔茨迭代进行正交化的法向分量，以减小不可行性。数值实验表明，与正交Procrustes和主成分分析等问题上的现有方法相比，该方法表现出优越的性能。 AI
影响 引入了一种更有效的涉及正交矩阵的问题的优化技术，可能使依赖于此类结构的机器学习算法受益。
排序理由 这是一篇详细介绍新数学优化方法的学术论文。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
arXiv:2605.02838v1 Announce Type: cross Abstract: Retraction-free approaches offer attractive low-cost alternatives to Riemannian methods on the Stiefel manifold, but they are often first-order, which may limit the efficiency under high-accuracy requirements. To this end, we prop…
Retraction-free approaches offer attractive low-cost alternatives to Riemannian methods on the Stiefel manifold, but they are often first-order, which may limit the efficiency under high-accuracy requirements. To this end, we propose a second-order method landing on the Stiefel m…
Retraction-free approaches offer attractive low-cost alternatives to Riemannian methods on the Stiefel manifold, but they are often first-order, which may limit the efficiency under high-accuracy requirements. To this end, we propose a second-order method landing on the Stiefel m…