High-order tensor completion via gradient-based optimization under tensor train format

Tensor train (TT) decomposition has drawn people’s attention due to its powerful representation ability and performance stability in high-order tensors. In this paper, we propose a novel approach to recover the missing entries of incomplete data represented by higher-order tensors. We attempt to fin...

Full description

Saved in:
Bibliographic Details
Published in:Signal processing. Image communication Vol. 73; pp. 53 - 61
Main Authors: Yuan, Longhao, Zhao, Qibin, Gui, Lihua, Cao, Jianting
Format: Journal Article
Language:English
Published: Amsterdam Elsevier B.V 01.04.2019
Elsevier BV
Subjects:
ISSN:0923-5965, 1879-2677
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Tensor train (TT) decomposition has drawn people’s attention due to its powerful representation ability and performance stability in high-order tensors. In this paper, we propose a novel approach to recover the missing entries of incomplete data represented by higher-order tensors. We attempt to find the low-rank TT decomposition of the incomplete data which captures the latent features of the whole data and then reconstruct the missing entries. By applying gradient descent algorithms, tensor completion problem is efficiently solved by optimization models. We propose two TT-based algorithms: Tensor Train Weighted Optimization (TT-WOPT) and Tensor Train Stochastic Gradient Descent (TT-SGD) to optimize TT decomposition factors. In addition, a method named Visual Data Tensorization (VDT) is proposed to transform visual data into higher-order tensors, resulting in the performance improvement of our algorithms. The experiments in synthetic data and visual data show high efficiency and performance of our algorithms compared to the state-of-the-art completion algorithms, especially in high-order, high missing rate, and large-scale tensor completion situations. •By employing tensor-train (TT) decomposition, we propose a gradientbased tensor completion algorithm named TT-WOPT which is of low computational complexity and shows high computational efficiency.•Based on stochastic gradient descent method, we propose the TT-SGD algorithm which possesses extremely low computational complexity in every iteration and can be applied to solving large-scale tensor completion problems.•We propose a higher-order tensorization method named VDT which transforms visual data into higher-order tensors. By applying the VDT method, the performance of TT-WOPT and TT-SGD are improved.
AbstractList Tensor train (TT) decomposition has drawn people’s attention due to its powerful representation ability and performance stability in high-order tensors. In this paper, we propose a novel approach to recover the missing entries of incomplete data represented by higher-order tensors. We attempt to find the low-rank TT decomposition of the incomplete data which captures the latent features of the whole data and then reconstruct the missing entries. By applying gradient descent algorithms, tensor completion problem is efficiently solved by optimization models. We propose two TT-based algorithms: Tensor Train Weighted Optimization (TT-WOPT) and Tensor Train Stochastic Gradient Descent (TT-SGD) to optimize TT decomposition factors. In addition, a method named Visual Data Tensorization (VDT) is proposed to transform visual data into higher-order tensors, resulting in the performance improvement of our algorithms. The experiments in synthetic data and visual data show high efficiency and performance of our algorithms compared to the state-of-the-art completion algorithms, especially in high-order, high missing rate, and large-scale tensor completion situations.
Tensor train (TT) decomposition has drawn people’s attention due to its powerful representation ability and performance stability in high-order tensors. In this paper, we propose a novel approach to recover the missing entries of incomplete data represented by higher-order tensors. We attempt to find the low-rank TT decomposition of the incomplete data which captures the latent features of the whole data and then reconstruct the missing entries. By applying gradient descent algorithms, tensor completion problem is efficiently solved by optimization models. We propose two TT-based algorithms: Tensor Train Weighted Optimization (TT-WOPT) and Tensor Train Stochastic Gradient Descent (TT-SGD) to optimize TT decomposition factors. In addition, a method named Visual Data Tensorization (VDT) is proposed to transform visual data into higher-order tensors, resulting in the performance improvement of our algorithms. The experiments in synthetic data and visual data show high efficiency and performance of our algorithms compared to the state-of-the-art completion algorithms, especially in high-order, high missing rate, and large-scale tensor completion situations. •By employing tensor-train (TT) decomposition, we propose a gradientbased tensor completion algorithm named TT-WOPT which is of low computational complexity and shows high computational efficiency.•Based on stochastic gradient descent method, we propose the TT-SGD algorithm which possesses extremely low computational complexity in every iteration and can be applied to solving large-scale tensor completion problems.•We propose a higher-order tensorization method named VDT which transforms visual data into higher-order tensors. By applying the VDT method, the performance of TT-WOPT and TT-SGD are improved.
Author Yuan, Longhao
Gui, Lihua
Zhao, Qibin
Cao, Jianting
Author_xml – sequence: 1
  givenname: Longhao
  orcidid: 0000-0002-0869-8445
  surname: Yuan
  fullname: Yuan, Longhao
  organization: Graduate School of Engineering, Saitama Institute of Technology, Japan
– sequence: 2
  givenname: Qibin
  orcidid: 0000-0002-4442-3182
  surname: Zhao
  fullname: Zhao, Qibin
  email: qibin.zhao@riken.jp
  organization: Tensor Learning Unit, RIKEN Center for Advanced Intelligence Project (AIP), Japan
– sequence: 3
  givenname: Lihua
  surname: Gui
  fullname: Gui, Lihua
  organization: Graduate School of Engineering, Saitama Institute of Technology, Japan
– sequence: 4
  givenname: Jianting
  surname: Cao
  fullname: Cao, Jianting
  email: cao@sit.ac.jp
  organization: Graduate School of Engineering, Saitama Institute of Technology, Japan
BookMark eNqFkD1PwzAQhi1UJNrCL2CJxJxwdmqnHhhQBRSpEguwWq59Ka6aONhuJfj1pC0DYoDphnuf-3hGZND6Fgm5pFBQoOJ6XbhGr7BgQKcFpQVQdkKGdFrJnImqGpAhSFbmXAp-RkYxrgGATUAOyevcrd5yHyyGLGEbfciMb7oNJufbbOd0tgraOmxTvtQRbea75Br3qQ_9bfuDS0G7Nqt9aHQ6J6e13kS8-K5j8nJ_9zyb54unh8fZ7SI3paxSXmsusbZCTjivOVZGLmUt2BJKbUuwFrQQojICDKNYT7kQhlsDegqcgcSyHJOr49wu-PctxqTWfhvafqVijLIKyn5yn5LHlAk-xoC1Mi4dPtjfvFEU1F6jWquDRrXXqChVvcaeLX-xXehT4eMf6uZIYf_8zmFQ0fQSDVoX0CRlvfuT_wKBypBt
CitedBy_id crossref_primary_10_1109_TIT_2024_3360951
crossref_primary_10_1016_j_image_2021_116276
crossref_primary_10_1016_j_sigpro_2025_110191
crossref_primary_10_1002_nla_2289
crossref_primary_10_1007_s11431_020_1851_5
crossref_primary_10_1109_TSP_2021_3085116
crossref_primary_10_1016_j_sigpro_2021_108425
crossref_primary_10_1016_j_sigpro_2022_108888
crossref_primary_10_1109_TIP_2021_3062195
crossref_primary_10_3389_feart_2022_1022874
crossref_primary_10_1109_JSTSP_2021_3051503
crossref_primary_10_1109_TCYB_2021_3108847
crossref_primary_10_1155_2022_7410364
crossref_primary_10_1007_s10444_024_10119_6
crossref_primary_10_1088_2632_2153_abad87
crossref_primary_10_3390_e26020105
crossref_primary_10_1007_s10915_023_02404_1
crossref_primary_10_3389_fdata_2024_1382144
crossref_primary_10_1109_TNNLS_2022_3181378
crossref_primary_10_1109_JIOT_2019_2960293
crossref_primary_10_1109_TCSVT_2021_3067022
crossref_primary_10_1109_TNSE_2022_3168615
crossref_primary_10_1109_LSP_2020_2990313
crossref_primary_10_1016_j_compbiomed_2023_106887
crossref_primary_10_1109_LSP_2025_3597829
crossref_primary_10_1109_TNNLS_2023_3236415
crossref_primary_10_1109_TIP_2021_3138325
crossref_primary_10_1007_s10092_024_00582_4
crossref_primary_10_1007_s10915_024_02670_7
crossref_primary_10_3389_frai_2021_687176
crossref_primary_10_1016_j_neucom_2025_130820
crossref_primary_10_1145_3278607
crossref_primary_10_3390_jmse9111245
crossref_primary_10_1016_j_neucom_2025_130889
Cites_doi 10.1145/192115.192132
10.1007/s11045-013-0269-9
10.1109/JSTSP.2015.2509907
10.1051/proc/201448001
10.1109/10.2119
10.1007/BF02289464
10.1016/j.sigpro.2004.11.029
10.1137/S0895479898346995
10.2172/989350
10.1109/TSP.2007.908929
10.1137/120868323
10.1109/TPAMI.2015.2392756
10.1109/TIP.2017.2672439
10.1137/07070111X
10.1016/j.chemolab.2010.08.004
10.1109/TPAMI.2012.39
10.1561/2200000059
10.1137/090752286
10.1109/TGRS.2013.2284280
ContentType Journal Article
Copyright 2018 Elsevier B.V.
Copyright Elsevier BV Apr 2019
Copyright_xml – notice: 2018 Elsevier B.V.
– notice: Copyright Elsevier BV Apr 2019
DBID AAYXX
CITATION
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
DOI 10.1016/j.image.2018.11.012
DatabaseName CrossRef
Computer and Information Systems Abstracts
Electronics & Communications Abstracts
Technology Research Database
ProQuest Computer Science Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
DatabaseTitle CrossRef
Technology Research Database
Computer and Information Systems Abstracts – Academic
Electronics & Communications Abstracts
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts Professional
DatabaseTitleList Technology Research Database

DeliveryMethod fulltext_linktorsrc
Discipline Applied Sciences
Engineering
Computer Science
EISSN 1879-2677
EndPage 61
ExternalDocumentID 10_1016_j_image_2018_11_012
S0923596518311081
GroupedDBID --K
--M
.DC
.~1
0R~
123
1B1
1~.
1~5
4.4
457
4G.
5VS
7-5
71M
8P~
9JN
AACTN
AAEDT
AAEDW
AAIAV
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAQXK
AAXUO
AAYFN
ABBOA
ABFNM
ABMAC
ABXDB
ABYKQ
ACDAQ
ACGFS
ACNNM
ACRLP
ACZNC
ADBBV
ADEZE
ADJOM
ADMUD
ADTZH
AEBSH
AECPX
AEKER
AFKWA
AFTJW
AGHFR
AGUBO
AGYEJ
AHHHB
AHJVU
AHZHX
AIALX
AIEXJ
AIKHN
AITUG
AJBFU
AJOXV
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
AOUOD
ASPBG
AVWKF
AXJTR
AZFZN
BJAXD
BKOJK
BLXMC
CS3
EBS
EFJIC
EFLBG
EJD
EO8
EO9
EP2
EP3
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
G-Q
G8K
GBLVA
GBOLZ
HLZ
HVGLF
HZ~
IHE
J1W
JJJVA
KOM
LG9
M41
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
PQQKQ
Q38
R2-
RIG
ROL
RPZ
SBC
SDF
SDG
SDP
SES
SEW
SPC
SPCBC
SST
SSV
SSZ
T5K
WUQ
XPP
ZMT
~G-
9DU
AATTM
AAXKI
AAYWO
AAYXX
ABDPE
ABWVN
ACLOT
ACRPL
ADNMO
AEIPS
AFJKZ
AGQPQ
AIIUN
ANKPU
APXCP
CITATION
EFKBS
~HD
7SC
7SP
8FD
AGCQF
JQ2
L7M
L~C
L~D
ID FETCH-LOGICAL-c397t-fa59efd69455f5e7c9b9f62b03ad30dd0a6667c60c21ef8566c5dc0a805209e33
ISICitedReferencesCount 49
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000463307000006&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0923-5965
IngestDate Wed Aug 13 11:21:47 EDT 2025
Sat Nov 29 07:17:49 EST 2025
Tue Nov 18 21:38:59 EST 2025
Fri Feb 23 02:28:17 EST 2024
IsPeerReviewed true
IsScholarly true
Keywords Tensor completion
Visual data recovery
Higher-order tensorization
Gradient-based optimization
Tensor train decomposition
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c397t-fa59efd69455f5e7c9b9f62b03ad30dd0a6667c60c21ef8566c5dc0a805209e33
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0002-0869-8445
0000-0002-4442-3182
PQID 2212703455
PQPubID 2045400
PageCount 9
ParticipantIDs proquest_journals_2212703455
crossref_citationtrail_10_1016_j_image_2018_11_012
crossref_primary_10_1016_j_image_2018_11_012
elsevier_sciencedirect_doi_10_1016_j_image_2018_11_012
PublicationCentury 2000
PublicationDate April 2019
2019-04-00
20190401
PublicationDateYYYYMMDD 2019-04-01
PublicationDate_xml – month: 04
  year: 2019
  text: April 2019
PublicationDecade 2010
PublicationPlace Amsterdam
PublicationPlace_xml – name: Amsterdam
PublicationTitle Signal processing. Image communication
PublicationYear 2019
Publisher Elsevier B.V
Elsevier BV
Publisher_xml – name: Elsevier B.V
– name: Elsevier BV
References Khoromskij (b38) 2015; 48
Maehara, Hayashi, Kawarabayashi (b31) 2016
De Lathauwer, De Moor, Vandewalle (b14) 2000; 21
Mocks (b9) 1988; 35
Wang, Aggarwal, Aeron (b25) 2017; 1
Moré, Thuente (b34) 1994; 20
Wright, Nocedal (b33) 1999; 35
Shashua, Hazan (b1) 2005
S. Ruder, An overview of gradient descent optimization algorithms. arXiv preprint
Gemulla, Nijkamp, Haas, Sismanis (b30) 2011
D. Kingma, J. Ba, Adam: A method for stochastic optimization. arXiv preprint
Kolda, Bader (b2) 2009; 51
Liu, Long, Zhu (b28) 2018
Bengua, Phien, Tuan, Do (b19) 2017; 26
Yang, Krompass, Tresp (b20) 2017
Q. Zhao, M. Sugiyama, A. Cichocki, Learning Efficient Tensor Representations with Ring Structure Networks. arXiv preprint
Sorber, Van Barel, De Lathauwer (b11) 2013; 23
Tucker (b13) 1966; 31
Zhang, He, Zhang, Shen, Yuan (b40) 2014; 52
Vasilescu, Terzopoulos (b3) 2003
Liu, Musialski, Wonka, Ye (b16) 2013; 35
De Lathauwer, Castaing (b7) 2008; 56
Q. Zhao, G. Zhou, S. Xie, L. Zhang, A. Cichocki, Tensor ring decomposition. arXiv preprint
Acar, Dunlavy, Kolda, Mørup (b5) 2011; 106
Muti, Bourennane (b8) 2005; 85
L. Yuan, J. Cao, Q. Wu, Q. Zhao, Higher-dimension Tensor Completion via Low-rank Tensor Ring Decomposition. arXiv preprint
Wang, Anandkumar (b32) 2016
Tsai, Saxe, Cox (b15) 2016
Shashua, Levin (b10) 2001
Oseledets (b18) 2011; 33
W. Wang, V. Aggarwal, S. Aeron, Tensor completion by alternating minimization under the tensor train (TT) model. arXiv preprint
Goulart, Boizard, Boyer, Favier, Comon (b12) 2016; 10
Franz, Schultz, Sizov, Staab (b4) 2009
.
J.I. Latorre, Image compression and entanglement. arXiv preprint quant-ph/0510031.
Zhao, Zhang, Cichocki (b6) 2015; 37
Filipović, Jukić (b17) 2015; 26
Yuan, Zhao, Cao (b22) 2017
L. Yuan, C. Li, D. Mandic, J. Cao, Q. Zhao, Tensor Ring Decomposition with Rank Minimization on Latent Space: An Efficient Approach for Tensor Completion. arXiv preprint
Cichocki, Lee, Oseledets, Phan, Zhao, Mandic (b29) 2016; 9
D.M. Dunlavy, T.G. Kolda, E. Acar, Poblano v1. 0: A matlab toolbox for gradient-based optimization, Sandia National Laboratories, Albuquerque, NM and Livermore, CA, Tech. Rep. SAND2010-1422.
Sorber (10.1016/j.image.2018.11.012_b11) 2013; 23
Muti (10.1016/j.image.2018.11.012_b8) 2005; 85
Yuan (10.1016/j.image.2018.11.012_b22) 2017
Oseledets (10.1016/j.image.2018.11.012_b18) 2011; 33
De Lathauwer (10.1016/j.image.2018.11.012_b14) 2000; 21
Shashua (10.1016/j.image.2018.11.012_b1) 2005
Shashua (10.1016/j.image.2018.11.012_b10) 2001
Gemulla (10.1016/j.image.2018.11.012_b30) 2011
Bengua (10.1016/j.image.2018.11.012_b19) 2017; 26
Cichocki (10.1016/j.image.2018.11.012_b29) 2016; 9
Liu (10.1016/j.image.2018.11.012_b16) 2013; 35
10.1016/j.image.2018.11.012_b39
Kolda (10.1016/j.image.2018.11.012_b2) 2009; 51
Moré (10.1016/j.image.2018.11.012_b34) 1994; 20
10.1016/j.image.2018.11.012_b37
Zhao (10.1016/j.image.2018.11.012_b6) 2015; 37
10.1016/j.image.2018.11.012_b24
Wright (10.1016/j.image.2018.11.012_b33) 1999; 35
10.1016/j.image.2018.11.012_b23
Yang (10.1016/j.image.2018.11.012_b20) 2017
10.1016/j.image.2018.11.012_b21
Wang (10.1016/j.image.2018.11.012_b25) 2017; 1
Filipović (10.1016/j.image.2018.11.012_b17) 2015; 26
Liu (10.1016/j.image.2018.11.012_b28) 2018
Maehara (10.1016/j.image.2018.11.012_b31) 2016
Acar (10.1016/j.image.2018.11.012_b5) 2011; 106
Wang (10.1016/j.image.2018.11.012_b32) 2016
Zhang (10.1016/j.image.2018.11.012_b40) 2014; 52
Tucker (10.1016/j.image.2018.11.012_b13) 1966; 31
Tsai (10.1016/j.image.2018.11.012_b15) 2016
De Lathauwer (10.1016/j.image.2018.11.012_b7) 2008; 56
Khoromskij (10.1016/j.image.2018.11.012_b38) 2015; 48
Vasilescu (10.1016/j.image.2018.11.012_b3) 2003
10.1016/j.image.2018.11.012_b27
Mocks (10.1016/j.image.2018.11.012_b9) 1988; 35
10.1016/j.image.2018.11.012_b26
10.1016/j.image.2018.11.012_b36
10.1016/j.image.2018.11.012_b35
Franz (10.1016/j.image.2018.11.012_b4) 2009
Goulart (10.1016/j.image.2018.11.012_b12) 2016; 10
References_xml – start-page: 792
  year: 2005
  end-page: 799
  ident: b1
  article-title: Non-negative tensor factorization with applications to statistics and computer vision
  publication-title: Proceedings of the 22nd International Conference on Machine Learning
– reference: J.I. Latorre, Image compression and entanglement. arXiv preprint quant-ph/0510031.
– volume: 23
  start-page: 695
  year: 2013
  end-page: 720
  ident: b11
  article-title: Optimization-based algorithms for tensor decompositions: Canonical polyadic decomposition, decomposition in rank-(L_r,L_r,1) terms, and a new generalization
  publication-title: SIAM J. Optim.
– reference: Q. Zhao, G. Zhou, S. Xie, L. Zhang, A. Cichocki, Tensor ring decomposition. arXiv preprint
– reference: L. Yuan, C. Li, D. Mandic, J. Cao, Q. Zhao, Tensor Ring Decomposition with Rank Minimization on Latent Space: An Efficient Approach for Tensor Completion. arXiv preprint
– volume: 26
  start-page: 677
  year: 2015
  end-page: 692
  ident: b17
  article-title: Tucker factorization with missing data with application to low-n-rank tensor completion
  publication-title: Multidimens. Syst. Signal Process.
– year: 2018
  ident: b28
  article-title: Image completion using low tensor tree rank and total variation minimization
  publication-title: IEEE Trans. Multimed.
– volume: 85
  start-page: 2338
  year: 2005
  end-page: 2353
  ident: b8
  article-title: Multidimensional filtering based on a tensor approach
  publication-title: Signal Process.
– reference: D.M. Dunlavy, T.G. Kolda, E. Acar, Poblano v1. 0: A matlab toolbox for gradient-based optimization, Sandia National Laboratories, Albuquerque, NM and Livermore, CA, Tech. Rep. SAND2010-1422.
– volume: 35
  start-page: 208
  year: 2013
  end-page: 220
  ident: b16
  article-title: Tensor completion for estimating missing values in visual data
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– volume: 26
  start-page: 2466
  year: 2017
  end-page: 2479
  ident: b19
  article-title: Efficient tensor completion for color image and video recovery: Low-rank tensor train
  publication-title: IEEE Trans. Image Process.
– volume: 21
  start-page: 1324
  year: 2000
  end-page: 1342
  ident: b14
  article-title: On the best rank-1 and rank-(r 1, r 2,..., rn) approximation of higher-order tensors
  publication-title: SIAM J. Matrix Anal. Appl.
– start-page: 2038
  year: 2016
  end-page: 2046
  ident: b15
  article-title: Tensor switching networks
  publication-title: Advances in Neural Information Processing Systems
– volume: 52
  start-page: 4729
  year: 2014
  end-page: 4743
  ident: b40
  article-title: Hyperspectral image restoration using low-rank matrix recovery
  publication-title: IEEE Trans. Geosci. Remote Sens.
– start-page: 3891
  year: 2017
  end-page: 3900
  ident: b20
  article-title: Tensor-Train Recurrent Neural Networks for Video Classification
  publication-title: International Conference on Machine Learning
– volume: 106
  start-page: 41
  year: 2011
  end-page: 56
  ident: b5
  article-title: Scalable tensor factorizations for incomplete data
  publication-title: Chemom. Intell. Lab. Syst.
– year: 2001
  ident: b10
  article-title: Linear image coding for regression and classification using the tensor-rank principle
  publication-title: Computer Vision and Pattern Recognition, 2001. CVPR 2001. Proceedings of the 2001 IEEE Computer Society Conference on, Vol. 1
– volume: 48
  start-page: 1
  year: 2015
  end-page: 28
  ident: b38
  article-title: Tensor numerical methods for multidimensional PDES: theoretical analysis and initial applications
  publication-title: ESAIM: Proc. Surv.
– start-page: 1919
  year: 2016
  end-page: 1925
  ident: b31
  article-title: Expected tensor decomposition with stochastic gradient descent
  publication-title: AAAI
– volume: 20
  start-page: 286
  year: 1994
  end-page: 307
  ident: b34
  article-title: Line search algorithms with guaranteed sufficient decrease
  publication-title: ACM Trans. Math. Softw. (TOMS)
– reference: W. Wang, V. Aggarwal, S. Aeron, Tensor completion by alternating minimization under the tensor train (TT) model. arXiv preprint
– volume: 31
  start-page: 279
  year: 1966
  end-page: 311
  ident: b13
  article-title: Some mathematical notes on three-mode factor analysis
  publication-title: Psychometrika
– reference: D. Kingma, J. Ba, Adam: A method for stochastic optimization. arXiv preprint
– volume: 33
  start-page: 2295
  year: 2011
  end-page: 2317
  ident: b18
  article-title: Tensor-train decomposition
  publication-title: SIAM J. Sci. Comput.
– volume: 35
  start-page: 482
  year: 1988
  end-page: 484
  ident: b9
  article-title: Topographic components model for event-related potentials and some biophysical considerations
  publication-title: IEEE Trans. Biomed. Eng.
– reference: Q. Zhao, M. Sugiyama, A. Cichocki, Learning Efficient Tensor Representations with Ring Structure Networks. arXiv preprint
– volume: 1
  start-page: 1
  year: 2017
  ident: b25
  article-title: Efficient low rank tensor ring completion
  publication-title: Rn
– reference: L. Yuan, J. Cao, Q. Wu, Q. Zhao, Higher-dimension Tensor Completion via Low-rank Tensor Ring Decomposition. arXiv preprint
– start-page: 3531
  year: 2016
  end-page: 3539
  ident: b32
  article-title: Online and differentially-private tensor decomposition
  publication-title: Advances in Neural Information Processing Systems
– volume: 56
  start-page: 1096
  year: 2008
  end-page: 1105
  ident: b7
  article-title: Blind identification of underdetermined mixtures by simultaneous matrix diagonalization
  publication-title: IEEE Trans. Signal Process.
– reference: .
– volume: 9
  start-page: 249
  year: 2016
  end-page: 429
  ident: b29
  article-title: Tensor networks for dimensionality reduction and large-scale optimization: Part 1 low-rank tensor decompositions
  publication-title: Found. Trends
– start-page: 213
  year: 2009
  end-page: 228
  ident: b4
  article-title: Triplerank: Ranking semantic web data by tensor decomposition
  publication-title: The Semantic Web-ISWC 2009
– reference: S. Ruder, An overview of gradient descent optimization algorithms. arXiv preprint
– volume: 51
  start-page: 455
  year: 2009
  end-page: 500
  ident: b2
  article-title: Tensor decompositions and applications
  publication-title: SIAM Rev.
– start-page: II
  year: 2003
  end-page: 93
  ident: b3
  article-title: Multilinear subspace analysis of image ensembles
  publication-title: Computer Vision and Pattern Recognition, 2003. Proceedings. 2003 IEEE Computer Society Conference on, Vol. 2
– volume: 10
  start-page: 757
  year: 2016
  end-page: 769
  ident: b12
  article-title: Tensor cp decomposition with structured factor matrices: Algorithms and Performance
  publication-title: IEEE J. Sel. Top. Sign. Proces.
– volume: 37
  start-page: 1751
  year: 2015
  end-page: 1763
  ident: b6
  article-title: Bayesian cp factorization of incomplete tensors with automatic rank determination
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– volume: 35
  start-page: 7
  year: 1999
  ident: b33
  article-title: Numerical optimization
  publication-title: Springer Sci.
– start-page: 222
  year: 2017
  end-page: 229
  ident: b22
  article-title: Completion of high order tensor data with missing entries via tensor-train decomposition
  publication-title: International Conference on Neural Information Processing
– start-page: 69
  year: 2011
  end-page: 77
  ident: b30
  article-title: Large-scale matrix factorization with distributed stochastic gradient descent
  publication-title: Proceedings of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
– ident: 10.1016/j.image.2018.11.012_b36
– start-page: II
  year: 2003
  ident: 10.1016/j.image.2018.11.012_b3
  article-title: Multilinear subspace analysis of image ensembles
– volume: 20
  start-page: 286
  issue: 3
  year: 1994
  ident: 10.1016/j.image.2018.11.012_b34
  article-title: Line search algorithms with guaranteed sufficient decrease
  publication-title: ACM Trans. Math. Softw. (TOMS)
  doi: 10.1145/192115.192132
– start-page: 1919
  year: 2016
  ident: 10.1016/j.image.2018.11.012_b31
  article-title: Expected tensor decomposition with stochastic gradient descent
– volume: 26
  start-page: 677
  issue: 3
  year: 2015
  ident: 10.1016/j.image.2018.11.012_b17
  article-title: Tucker factorization with missing data with application to low-n-rank tensor completion
  publication-title: Multidimens. Syst. Signal Process.
  doi: 10.1007/s11045-013-0269-9
– volume: 10
  start-page: 757
  issue: 4
  year: 2016
  ident: 10.1016/j.image.2018.11.012_b12
  article-title: Tensor cp decomposition with structured factor matrices: Algorithms and Performance
  publication-title: IEEE J. Sel. Top. Sign. Proces.
  doi: 10.1109/JSTSP.2015.2509907
– volume: 48
  start-page: 1
  year: 2015
  ident: 10.1016/j.image.2018.11.012_b38
  article-title: Tensor numerical methods for multidimensional PDES: theoretical analysis and initial applications
  publication-title: ESAIM: Proc. Surv.
  doi: 10.1051/proc/201448001
– volume: 35
  start-page: 482
  issue: 6
  year: 1988
  ident: 10.1016/j.image.2018.11.012_b9
  article-title: Topographic components model for event-related potentials and some biophysical considerations
  publication-title: IEEE Trans. Biomed. Eng.
  doi: 10.1109/10.2119
– volume: 31
  start-page: 279
  issue: 3
  year: 1966
  ident: 10.1016/j.image.2018.11.012_b13
  article-title: Some mathematical notes on three-mode factor analysis
  publication-title: Psychometrika
  doi: 10.1007/BF02289464
– start-page: 213
  year: 2009
  ident: 10.1016/j.image.2018.11.012_b4
  article-title: Triplerank: Ranking semantic web data by tensor decomposition
– volume: 85
  start-page: 2338
  issue: 12
  year: 2005
  ident: 10.1016/j.image.2018.11.012_b8
  article-title: Multidimensional filtering based on a tensor approach
  publication-title: Signal Process.
  doi: 10.1016/j.sigpro.2004.11.029
– ident: 10.1016/j.image.2018.11.012_b26
– volume: 21
  start-page: 1324
  issue: 4
  year: 2000
  ident: 10.1016/j.image.2018.11.012_b14
  article-title: On the best rank-1 and rank-(r 1, r 2,..., rn) approximation of higher-order tensors
  publication-title: SIAM J. Matrix Anal. Appl.
  doi: 10.1137/S0895479898346995
– ident: 10.1016/j.image.2018.11.012_b24
– ident: 10.1016/j.image.2018.11.012_b35
  doi: 10.2172/989350
– volume: 56
  start-page: 1096
  issue: 3
  year: 2008
  ident: 10.1016/j.image.2018.11.012_b7
  article-title: Blind identification of underdetermined mixtures by simultaneous matrix diagonalization
  publication-title: IEEE Trans. Signal Process.
  doi: 10.1109/TSP.2007.908929
– year: 2001
  ident: 10.1016/j.image.2018.11.012_b10
  article-title: Linear image coding for regression and classification using the tensor-rank principle
– volume: 23
  start-page: 695
  issue: 2
  year: 2013
  ident: 10.1016/j.image.2018.11.012_b11
  article-title: Optimization-based algorithms for tensor decompositions: Canonical polyadic decomposition, decomposition in rank-(L_r,L_r,1) terms, and a new generalization
  publication-title: SIAM J. Optim.
  doi: 10.1137/120868323
– volume: 37
  start-page: 1751
  issue: 9
  year: 2015
  ident: 10.1016/j.image.2018.11.012_b6
  article-title: Bayesian cp factorization of incomplete tensors with automatic rank determination
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2015.2392756
– volume: 26
  start-page: 2466
  issue: 5
  year: 2017
  ident: 10.1016/j.image.2018.11.012_b19
  article-title: Efficient tensor completion for color image and video recovery: Low-rank tensor train
  publication-title: IEEE Trans. Image Process.
  doi: 10.1109/TIP.2017.2672439
– start-page: 69
  year: 2011
  ident: 10.1016/j.image.2018.11.012_b30
  article-title: Large-scale matrix factorization with distributed stochastic gradient descent
– start-page: 2038
  year: 2016
  ident: 10.1016/j.image.2018.11.012_b15
  article-title: Tensor switching networks
– volume: 1
  start-page: 1
  issue: r1
  year: 2017
  ident: 10.1016/j.image.2018.11.012_b25
  article-title: Efficient low rank tensor ring completion
  publication-title: Rn
– start-page: 3891
  year: 2017
  ident: 10.1016/j.image.2018.11.012_b20
  article-title: Tensor-Train Recurrent Neural Networks for Video Classification
– ident: 10.1016/j.image.2018.11.012_b39
– volume: 51
  start-page: 455
  issue: 3
  year: 2009
  ident: 10.1016/j.image.2018.11.012_b2
  article-title: Tensor decompositions and applications
  publication-title: SIAM Rev.
  doi: 10.1137/07070111X
– volume: 106
  start-page: 41
  issue: 1
  year: 2011
  ident: 10.1016/j.image.2018.11.012_b5
  article-title: Scalable tensor factorizations for incomplete data
  publication-title: Chemom. Intell. Lab. Syst.
  doi: 10.1016/j.chemolab.2010.08.004
– ident: 10.1016/j.image.2018.11.012_b37
– volume: 35
  start-page: 7
  issue: 67–68
  year: 1999
  ident: 10.1016/j.image.2018.11.012_b33
  article-title: Numerical optimization
  publication-title: Springer Sci.
– start-page: 792
  year: 2005
  ident: 10.1016/j.image.2018.11.012_b1
  article-title: Non-negative tensor factorization with applications to statistics and computer vision
– volume: 35
  start-page: 208
  issue: 1
  year: 2013
  ident: 10.1016/j.image.2018.11.012_b16
  article-title: Tensor completion for estimating missing values in visual data
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2012.39
– ident: 10.1016/j.image.2018.11.012_b27
– volume: 9
  start-page: 249
  issue: 4–5
  year: 2016
  ident: 10.1016/j.image.2018.11.012_b29
  article-title: Tensor networks for dimensionality reduction and large-scale optimization: Part 1 low-rank tensor decompositions
  publication-title: Found. Trends® Mach. Learn.
  doi: 10.1561/2200000059
– start-page: 3531
  year: 2016
  ident: 10.1016/j.image.2018.11.012_b32
  article-title: Online and differentially-private tensor decomposition
– ident: 10.1016/j.image.2018.11.012_b21
– year: 2018
  ident: 10.1016/j.image.2018.11.012_b28
  article-title: Image completion using low tensor tree rank and total variation minimization
  publication-title: IEEE Trans. Multimed.
– volume: 33
  start-page: 2295
  issue: 5
  year: 2011
  ident: 10.1016/j.image.2018.11.012_b18
  article-title: Tensor-train decomposition
  publication-title: SIAM J. Sci. Comput.
  doi: 10.1137/090752286
– ident: 10.1016/j.image.2018.11.012_b23
– volume: 52
  start-page: 4729
  issue: 8
  year: 2014
  ident: 10.1016/j.image.2018.11.012_b40
  article-title: Hyperspectral image restoration using low-rank matrix recovery
  publication-title: IEEE Trans. Geosci. Remote Sens.
  doi: 10.1109/TGRS.2013.2284280
– start-page: 222
  year: 2017
  ident: 10.1016/j.image.2018.11.012_b22
  article-title: Completion of high order tensor data with missing entries via tensor-train decomposition
SSID ssj0002409
Score 2.4761908
Snippet Tensor train (TT) decomposition has drawn people’s attention due to its powerful representation ability and performance stability in high-order tensors. In...
SourceID proquest
crossref
elsevier
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 53
SubjectTerms Algorithms
Decomposition
Gradient-based optimization
Higher-order tensorization
Mathematical analysis
Optimization
Tensor completion
Tensor train decomposition
Tensors
Visual data recovery
Title High-order tensor completion via gradient-based optimization under tensor train format
URI https://dx.doi.org/10.1016/j.image.2018.11.012
https://www.proquest.com/docview/2212703455
Volume 73
WOSCitedRecordID wos000463307000006&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals 2021
  customDbUrl:
  eissn: 1879-2677
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002409
  issn: 0923-5965
  databaseCode: AIEXJ
  dateStart: 19950201
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Nb9NAEF2FlAMcChQQLQX5gLiEjdbf3mOFUmhVBRBpldtqvV6nrlo7JE7UH8GPZvbDjktFBAcuVrTxxo7fy-zM5s0MQu9EkHCZSw97GY9xkKQCp5JyAMRNgT7goFCum03E43EyndKvvd7PJhdmfR2XZXJ7S-f_FWoYA7BV6uw_wN1-KAzAawAdjgA7HP8KeKXcwLqi5kCp06uFkY1LDfS64IPZQsu8aqxWsGxQgdG4sdmYuituO0-3j7DpjV0n9nsxUz7s3OQYqM4Lg5Mbpf0R3WyT1p6sbHpDVc4uedXZqda7tN-KtGjP_bQyydrF5WqjIDLnnQKP62adtdsULu2oW_TeWZs_c9Hdg_R8HFLTLGIojQVOYoq9yPZ2sSY69js21hQXvmf6zS7E1bBQX1hp9pKhKs9qRdp3Cm2Pv7Dj87MzNhlNJ-_nP7DqQab-q7cNWR6gHQ_CKNJHO0cno-lpu7KD92NqN9rbbqpYab3gvev-ydP5bc3XjszkKdq1EYhzZJjzDPVkuYee2GjEsbZ-CUNNw49mbA897lSvfI4uNkxzDGOcDdMcYJpzl2lOl2mOZlozTzPNMUx7gc6PR5OPn7Ft04EFOLM1znlIZZ5FNAjDPJSxoCnNIy8lPs98kmWEQ4gci4gIz5V5AvGDCDNBeKIlWNL3X6J-WZXyFXI4CbgvXZJyPw8iCC5UV6uQZIGbRzwT3j7ymkfKhK1hr-7wmjVixSumcWAKB4huGeCwjz60k-amhMv206MGK2a9UONdMmDa9omHDbLM2oMl81QHBeLDoznY_vZr9GjzszlE_Xqxkm_QQ7Gui-XirWXiL1COs78
linkProvider Elsevier
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=High-order+tensor+completion+via+gradient-based+optimization+under+tensor+train+format&rft.jtitle=Signal+processing.+Image+communication&rft.au=Yuan%2C+Longhao&rft.au=Zhao%2C+Qibin&rft.au=Gui%2C+Lihua&rft.au=Cao%2C+Jianting&rft.date=2019-04-01&rft.pub=Elsevier+BV&rft.issn=0923-5965&rft.eissn=1879-2677&rft.volume=73&rft.spage=53&rft_id=info:doi/10.1016%2Fj.image.2018.11.012&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0923-5965&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0923-5965&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0923-5965&client=summon