Learning Unbalanced and Sparse Low-Order Tensors

Hoang, PM; Tuan, HD; Son, TT; Poor, HV; Hanzo, L

Learning Unbalanced and Sparse Low-Order Tensors

Hoang, PM Tuan, HD Son, TT Poor, HV Hanzo, L

Permalink

Publisher:: IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Publication Type:: Journal Article
Citation:: IEEE Transactions on Signal Processing, 2022, 70, pp. 5624-5638
Issue Date:: 2022-01-01

Closed Access

	Filename	Description	Size
	Learning_Unbalanced_and_Sparse_Low-Order_Tensors.pdf	Published version	8.24 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Hoang, PM
dc.contributor.author	Tuan, HD
dc.contributor.author	Son, TT
dc.contributor.author	Poor, HV
dc.contributor.author	Hanzo, L
dc.date.accessioned	2023-04-13T03:47:09Z
dc.date.available	2023-04-13T03:47:09Z
dc.date.issued	2022-01-01
dc.identifier.citation	IEEE Transactions on Signal Processing, 2022, 70, pp. 5624-5638
dc.identifier.issn	1053-587X
dc.identifier.issn	1941-0476
dc.identifier.uri	http://hdl.handle.net/10453/169749
dc.description.abstract	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.
dc.language	English
dc.publisher	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
dc.relation	http://purl.org/au-research/grants/arc/DP190102501
dc.relation.ispartof	IEEE Transactions on Signal Processing
dc.relation.isbasedon	10.1109/TSP.2022.3221661
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject.classification	Networking & Telecommunications
dc.title	Learning Unbalanced and Sparse Low-Order Tensors
dc.type	Journal Article
utslib.citation.volume	70
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Electrical and Data Engineering
utslib.copyright.status	closed_access	*
dc.date.updated	2023-04-13T03:47:07Z
pubs.publication-status	Published
pubs.volume	70

Abstract:

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.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/169749