English

Riemannian preconditioning for tensor completion

Numerical Analysis 2016-05-30 v2 Machine Learning Optimization and Control

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.

Keywords

Cite

@article{arxiv.1506.02159,
  title  = {Riemannian preconditioning for tensor completion},
  author = {Hiroyuki Kasai and Bamdev Mishra},
  journal= {arXiv preprint arXiv:1506.02159},
  year   = {2016}
}

Comments

Supplementary material included in the paper. An extension of the paper is in arXiv:1605.08257

R2 v1 2026-06-22T09:48:29.618Z