English

A Tight Lower Bound for the Approximation Guarantee of Higher-Order Singular Value Decomposition

Data Structures and Algorithms 2025-08-12 v1 Machine Learning

Abstract

We prove that the classic approximation guarantee for the higher-order singular value decomposition (HOSVD) is tight by constructing a tensor for which HOSVD achieves an approximation ratio of N/(1+ε)N/(1+\varepsilon), for any ε>0\varepsilon > 0. This matches the upper bound of De Lathauwer et al. (2000a) and shows that the approximation ratio of HOSVD cannot be improved. Using a more advanced construction, we also prove that the approximation guarantees for the ST-HOSVD algorithm of Vannieuwenhoven et al. (2012) and higher-order orthogonal iteration (HOOI) of De Lathauwer et al. (2000b) are tight by showing that they can achieve their worst-case approximation ratio of N/(1+ε)N / (1 + \varepsilon), for any ε>0\varepsilon > 0.

Keywords

Cite

@article{arxiv.2508.06693,
  title  = {A Tight Lower Bound for the Approximation Guarantee of Higher-Order Singular Value Decomposition},
  author = {Matthew Fahrbach and Mehrdad Ghadiri},
  journal= {arXiv preprint arXiv:2508.06693},
  year   = {2025}
}

Comments

15 pages