A Random Matrix Approach to Low-Multilinear-Rank Tensor Approximation
Lebeau, Hugo, Chatelain, Florent, Couillet, Romain
–arXiv.org Artificial Intelligence
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 $1$ in the large-dimensional limit.
arXiv.org Artificial Intelligence
Feb-5-2024
- Country:
- North America > United States
- New York > New York County > New York City (0.04)
- Europe
- Russia (0.04)
- United Kingdom > England
- Cambridgeshire > Cambridge (0.04)
- Oxfordshire > Oxford (0.04)
- France > Auvergne-Rhône-Alpes
- Asia
- Russia (0.04)
- Middle East > Republic of Türkiye
- Bingoel Province > Bingol (0.04)
- Africa
- Senegal > Kolda Region
- Kolda (0.04)
- Middle East > Tunisia
- Ben Arous Governorate > Ben Arous (0.04)
- Senegal > Kolda Region
- North America > United States
- Genre:
- Research Report > New Finding (0.46)
- Industry:
- Technology: