2017/07/05 by Dong Xia, Fan Zhou, Xia, Dong +1
Chemistry · Computer Science · Mathematics · Physics and Astronomy · #Advanced NMR Techniques and Applications #FOS: Computer and information sciences #FOS: Mathematics #Information Theory (cs.IT) #Machine Learning (stat.ML) #Probability (math.PR) #Solar and Space Plasma Dynamics #Statistics Theory (math.ST) #Tensor decomposition and applications #cs.IT #math.IT #math.PR #math.ST #stat.ML #stat.TH
paper · pdf · doi:10.48550/arxiv.1707.01207
openalex publication_date 2017/07/05 · arxiv created 2019/01/01 · arxiv updated 2019/01/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
The higher order singular value decomposition (HOSVD) of tensors is a generalization of matrix SVD. The perturbation analysis of HOSVD under random noise is more delicate than its matrix counterpart. Recently, polynomial time algorithms have been proposed where statistically optimal estimates of the singular subspaces and the low rank tensors are attainable in the Euclidean norm. In this article, we analyze the sup-norm perturbation bounds of HOSVD and introduce estimators of the singular subspaces with sharp deviation bounds in the sup-norm. We also investigate a low rank tensor denoising estimator and demonstrate its fast convergence rate with respect to the entry-wise errors. The sup-norm perturbation bounds reveal unconventional phase transitions for statistical learning applications such as the exact clustering in high dimensional Gaussian mixture model and the exact support recovery in sub-tensor localizations. In addition, the bounds established for HOSVD also elaborate the one-sided sup-norm perturbation bounds for the singular subspaces of unbalanced (or fat) matrices.