A Riemannian trust-region method for low-rank tensor completion

DOI10.1002/NLA.2175arXiv1703.10019WikidataQ115405343 ScholiaQ115405343MaRDI QIDQ6284928FDOQ6284928

Publication date: 29 March 2017

Abstract: The goal of tensor completion is to fill in missing entries of a partially known tensor (possibly including some noise) under a low-rank constraint. This may be formulated as a least-squares problem. The set of tensors of a given multilinear rank is known to admit a Riemannian manifold structure, thus methods of Riemannian optimization are applicable. In our work, we derive the Riemannian Hessian of an objective function on the low-rank tensor manifolds using the Weingarten map, a concept from differential geometry. We discuss the convergence properties of Riemannian trust-region methods based on the exact Hessian and standard approximations, both theoretically and numerically. We compare our approach to Riemannian tensor completion methods from recent literature, both in terms of convergence behaviour and computational complexity. Our examples include the completion of randomly generated data with and without noise and recovery of multilinear data from survey statistics.

Mathematics Subject Classification ID

Numerical optimization and variational techniques (65K10) Multilinear algebra, tensor calculus (15A69)

This page was built for publication: A Riemannian trust-region method for low-rank tensor completion

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6284928)