English

A Random Matrix Approach to Low-Multilinear-Rank Tensor Approximation

Machine Learning 2025-01-15 v3 Machine Learning Probability

Abstract

This work presents a comprehensive understanding of the estimation of a planted low-rank signal from a general spiked tensor model near the computational threshold. Relying on standard tools from the theory of large random matrices, we characterize the large-dimensional spectral behavior of the unfoldings of the data tensor and exhibit relevant signal-to-noise ratios governing the detectability of the principal directions of the signal. These results allow to accurately predict the reconstruction performance of truncated multilinear SVD (MLSVD) in the non-trivial regime. This is particularly important since it serves as an initialization of the higher-order orthogonal iteration (HOOI) scheme, whose convergence to the best low-multilinear-rank approximation depends entirely on its initialization. We give a sufficient condition for the convergence of HOOI and show that the number of iterations before convergence tends to 11 in the large-dimensional limit.

Keywords

Cite

@article{arxiv.2402.03169,
  title  = {A Random Matrix Approach to Low-Multilinear-Rank Tensor Approximation},
  author = {Hugo Lebeau and Florent Chatelain and Romain Couillet},
  journal= {arXiv preprint arXiv:2402.03169},
  year   = {2025}
}
R2 v1 2026-06-28T14:38:47.561Z