2021/12/23 by Mohamed El Amine Seddik, Maxime Guillaud, Seddik, Mohamed El Amine +3
Mathematics · Medicine · Physics and Astronomy · #Advanced Neuroimaging Techniques and Applications #Electromagnetic Scattering and Analysis #FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (stat.ML) #Probability (math.PR) #Spectral Theory (math.SP) #Tensor decomposition and applications
paper · pdf · doi:10.48550/arxiv.2112.12348
openalex publication_date 2021/12/23 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Relying on random matrix theory (RMT), this paper studies asymmetric order-d spiked tensor models with Gaussian noise. Using the variational definition of the singular vectors and values of (Lim, 2005), we show that the analysis of the considered model boils down to the analysis of an equivalent spiked symmetric block-wise random matrix, that is constructed from contractions of the studied tensor with the singular vectors associated to its best rank-1 approximation. Our approach allows the exact characterization of the almost sure asymptotic singular value and alignments of the corresponding singular vectors with the true spike components, when \fracni∑j=1d nj→ ci∈ (0, 1) with ni's the tensor dimensions. In contrast to other works that rely mostly on tools from statistical physics to study random tensors, our results rely solely on classical RMT tools such as Stein's lemma. Finally, classical RMT results concerning spiked random matrices are recovered as a particular case.