Robust Multilinear Tensor Rank Estimation Using Higher Order Singular Value Decomposition and Information Criteria

Tatsuya Yokota, Namgil Lee, Andrzej Cichocki

Research output: Contribution to journalArticlepeer-review

43 Citations (Scopus)

Abstract

Model selection in tensor decomposition is important for real applications if the rank of the original data tensor is unknown and the observed tensor is noisy. In the Tucker model, the minimum description length (MDL) or Bayesian information criteria have been applied to tensors via matrix unfolding, but these methods are sensitive to noise when the tensors have a multilinear low rank structure given by the Tucker model. In this study, we propose new methods for improving the MDL so it is more robust to noise. The proposed methods are justified theoretically by analyzing the "multilinear low-rank structure" of tensors. Extensive experiments including numerical simulations and a real application to image denoising are provided to illustrate the advantages of the proposed methods.

Original languageEnglish
Article number7676397
Pages (from-to)1196-1206
Number of pages11
JournalIEEE Transactions on Signal Processing
Volume65
Issue number5
DOIs
Publication statusPublished - 1 Mar 2017
Externally publishedYes

Keywords

  • Bayesian information criterion (BIC)
  • higher order singular value decomposition (HOSVD)
  • minimum description length (MDL)
  • model selection
  • multilinear tensor rank
  • Tucker decomposition

Fingerprint

Dive into the research topics of 'Robust Multilinear Tensor Rank Estimation Using Higher Order Singular Value Decomposition and Information Criteria'. Together they form a unique fingerprint.

Cite this