Sparse Nonnegative Tensor Factorization and Completion With Noisy Observations

DOI10.1109/TIT.2022.3142846MaRDI QIDQ5088403zbMATH OpenOpenAlexWikidataFDO

Authors Xiongjun Zhang, Michael Ng

Publication date 13 July 2022

Published in IEEE Transactions on Information Theory (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2007.10626

zbMATH Keywords

completion problemerror boundspartial and noisy observations for third-order tensorssparse nonnegative tensor factorization

Mathematics Subject Classification ID

Factorization of matrices (15A23) Multilinear algebra, tensor calculus (15A69) Linear regression; mixed models (62J05) Numerical linear algebra (65F99)

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 $el{l}_0$ 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.

Cited in

(9)

• Nonconvex Low-Rank Tensor Completion from Noisy Data
• Tensor factorization via transformed tensor-tensor product for image alignment
• Covariate-Assisted Sparse Tensor Completion
• \(H\)-eigenvalue inclusion sets for sparse tensors
• Self representation based methods for tensor completion problem
• A composite optimization algorithm for Poisson tensor completions without nonnegative constraints based on the generalized Gauss-Newton method
• Accurate regularized Tucker decomposition for image restoration
• Poisson tensor completion via nonconvex regularization and nonlocal self-similarity for multi-dimensional image recovery
• Accelerated FCTN with perturbed periodic second-order discrete difference regularization for tensor completion

This page was built for publication: Sparse Nonnegative Tensor Factorization and Completion With Noisy Observations

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5088403)