arXiv cs.AI by Synapse Flow 編集部

A second-order method landing on the Stiefel manifold via Newton$\unicode{x2013}$Schulz iteration

概要

arXiv:2605.02838v2 Announce Type: replace-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 propose a secon…

元記事を読む →

関連記事