Comment on "First-order methods almost always avoid strict saddle points"
From MaRDI portal
Abstract: 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.
This page was built for publication: Comment on "First-order methods almost always avoid strict saddle points"
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6395417)
