pith. sign in

arxiv: 1506.02159 · v2 · pith:SY7XQCTOnew · submitted 2015-06-06 · 💻 cs.NA · cs.LG· math.OC

Riemannian preconditioning for tensor completion

classification 💻 cs.NA cs.LGmath.OC
keywords riemannianproblemalgorithmcompletionmetricpreconditioningproposedtensor
0
0 comments X
read the original abstract

We propose a novel Riemannian preconditioning approach for the tensor completion problem with rank constraint. A Riemannian metric or inner product is proposed that exploits the least-squares structure of the cost function and takes into account the structured symmetry in Tucker decomposition. The specific metric allows to use the versatile framework of Riemannian optimization on quotient manifolds to develop a preconditioned nonlinear conjugate gradient algorithm for the problem. To this end, concrete matrix representations of various optimization-related ingredients are listed. Numerical comparisons suggest that our proposed algorithm robustly outperforms state-of-the-art algorithms across different problem instances encompassing various synthetic and real-world datasets.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.