论文标题
评论“一阶方法几乎总是避免严格的马鞍点”
Comment on "First-order methods almost always avoid strict saddle points"
论文作者
论文摘要
由于Lee等人，Riemannian梯度下降方法在多种梯度优化中的全球稳定性分析（即，几乎所有初始化）的分析。 （Math。Program。176：311-337）被纠正。此外，新引入的回缩l-Smooth属性提出了对踏板大小的明确绑定。
The analysis on the global stability of Riemannian gradient descent method in manifold optimization (i.e., it avoids strict saddle points for almost all initializations) due to Lee et al. (Math. Program. 176:311-337) is corrected. Moreover, an explicit bound on the step-size is presented by the newly introduced retraction L-smooth property.
