Learning Unbalanced and Sparse Low-Order Tensors

Pham Minh Hoang, Hoang Duong Tuan, Tran Thai Son, H. Vincent Poor, Lajos Hanzo

Research output: Contribution to journalArticlepeer-review


Efficient techniques are developed for completing unbalanced and sparse low-order tensors, which cannot be effectively completed by popular matrix-rank optimization based techniques such as compressed sensing and/or the ℓq-matrix-metric. We use our previously developed 2D-index encoding technique for tensor augmentation in order to represent these incomplete low-order tensors by high-order but low-dimensional tensors with their modes building up a coarse-grained hierachy of correlations among the incomplete tensor entries. The concept of tensor-trains is then exploited for decomposing these augmented tensors into trains of balanced and sparse matrices for efficient completion. More explicitly, we develop powerful algorithms exhibiting an excellent performance vs. complexity trade-off, which are supported by numerical examples by relying on matrix data and third-order tensor data derived from color image pixels.

Original languageEnglish (US)
Pages (from-to)5624-5638
Number of pages15
JournalIEEE Transactions on Signal Processing
StatePublished - 2022
Externally publishedYes

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Electrical and Electronic Engineering


  • Matrix and/or low-order tensor completion
  • tensor train decomposition
  • tensor train rank


Dive into the research topics of 'Learning Unbalanced and Sparse Low-Order Tensors'. Together they form a unique fingerprint.

Cite this