Sparse Nonnegative Tensor Factorization and Completion with Noisy Observations

Xiongjun Zhang*, Michael K. Ng

*Corresponding author for this work

Research output: Contribution to journalJournal articlepeer-review

13 Citations (Scopus)

Abstract

In this paper, we study the sparse nonnegative tensor factorization and completion problem from partial and noisy observations for third-order tensors. Because of sparsity and nonnegativity, the underlying tensor is decomposed into the tensor-tensor product of one sparse nonnegative tensor and one nonnegative tensor. We propose to minimize the sum of the maximum likelihood estimation for the observations with nonnegativity constraints and the tensor l0 norm for the sparse factor. We show that the error bounds of the estimator of the proposed model can be established under general noise observations. The detailed error bounds under specific noise distributions including additive Gaussian noise, additive Laplace noise, and Poisson observations can be derived. Moreover, the minimax lower bounds are shown to be matched with the established upper bounds up to a logarithmic factor of the sizes of the underlying tensor. These theoretical results for tensors are better than those obtained for matrices, and this illustrates the advantage of the use of nonnegative sparse tensor models for completion and denoising. Numerical experiments are provided to validate the superiority of the proposed tensor-based method compared with the matrix-based approach.

Original languageEnglish
Pages (from-to)2551-2572
Number of pages22
JournalIEEE Transactions on Information Theory
Volume68
Issue number4
Early online date13 Jan 2022
DOIs
Publication statusPublished - Apr 2022

Scopus Subject Areas

  • Information Systems
  • Computer Science Applications
  • Library and Information Sciences

User-Defined Keywords

  • error bound
  • maximum likelihood estimation
  • Sparse nonnegative tensor factorization and completion
  • tensor-tensor product

Fingerprint

Dive into the research topics of 'Sparse Nonnegative Tensor Factorization and Completion with Noisy Observations'. Together they form a unique fingerprint.

Cite this