arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.09058math.OCmath.DS
收藏

降落在Stiefel管汇上的Optimization流

Optimization flows landing on the Stiefel manifold

Bin Gao, Simon Vary, Pierre Ablin, P. -A. Absil

摘要:

我们研究了一个连续时间系统,它解决了正交矩阵集上的最优化问题,也被称为Stiefel流形。所得到的优化流遵循的路径并不总是在流形上,而是渐进地落在流形上。我们引入了一个广义Stiefel流形,我们推广的Stiefel流形的典范度量。我们证明了所提出的流的向量场可以被解释为广义Stiefel流形上的黎曼梯度与法向量之和。证明了该流全局收敛于临界点集,且任何局部极小值和孤立的临界点都是渐近稳定的.

英文摘要:

We study a continuous-time system that solves optimization problems over the set of orthonormal matrices, which is also known as the Stiefel manifold. The resulting optimization flow follows a path that is not always on the manifold but asymptotically lands on the manifold. We introduce a generalized Stiefel manifold to which we extend the canonical metric of the Stiefel manifold. We show that the vector field of the proposed flow can be interpreted as the sum of a Riemannian gradient on a generalized Stiefel manifold and a normal vector. Moreover, we prove that the proposed flow globally converges to the set of critical points, and any local minimum and isolated critical point is asymptotically stable.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑