Asymptotic Escape of Spurious Critical Points on the Low-rank Matrix Manifold [article]

Thomas Y. Hou, Zhenzhen Li, Ziyun Zhang
2022 arXiv   pre-print
We show that on the manifold of fixed-rank and symmetric positive semi-definite matrices, the Riemannian gradient descent algorithm almost surely escapes some spurious critical points on the boundary of the manifold. Our result is the first to partially overcome the incompleteness of the low-rank matrix manifold without changing the vanilla Riemannian gradient descent algorithm. The spurious critical points are some rank-deficient matrices that capture only part of the eigen components of the
more » ... ound truth. Unlike classical strict saddle points, they exhibit very singular behavior. We show that using the dynamical low-rank approximation and a rescaled gradient flow, some of the spurious critical points can be converted to classical strict saddle points in the parameterized domain, which leads to the desired result. Numerical experiments are provided to support our theoretical findings.
arXiv:2107.09207v2 fatcat:yx2fksiby5galjj3jubsfbmnvq