Geometric design of the tangent term in landing algorithms for orthogonality constraints

Goyens, Florentin, Absil, P. -A., Feppon, Florian

arXiv.org Machine Learning 

We propose a family a metrics over the set of full-rank $n\times p$ real matrices, and apply them to the landing framework for optimization under orthogonality constraints. The family of metrics we propose is a natural extension of the $β$-metric, defined on the Stiefel manifold.

Duplicate Docs Excel Report

Title
None found

Similar Docs  Excel Report  more

TitleSimilaritySource
None found