English

Rank Estimation for Third-Order Tensor Completion in the Tensor-Train Format

Optimization and Control 2024-09-10 v1

Abstract

We propose a numerical method to obtain an adequate value for the upper bound on the rank for the tensor completion problem on the variety of third-order tensors of bounded tensor-train rank. The method is inspired by the parametrization of the tangent cone derived by Kutschan (2018). A proof of the adequacy of the upper bound for a related low-rank tensor approximation problem is given and an estimated rank is defined to extend the result to the low-rank tensor completion problem. Some experiments on synthetic data illustrate the approach and show that the method is very robust, e.g., to noise on the data.

Keywords

Cite

@article{arxiv.2309.15170,
  title  = {Rank Estimation for Third-Order Tensor Completion in the Tensor-Train Format},
  author = {Charlotte Vermeylen and Guillaume Olikier and P. -A. Absil and Marc Van Barel},
  journal= {arXiv preprint arXiv:2309.15170},
  year   = {2024}
}
R2 v1 2026-06-28T12:33:04.591Z