Randomized algorithms for fast computation of low rank tensor ring model

被引：19

作者：

Ahmadi-Asl, Salman ^{[1
]}

Cichocki, Andrzej ^{[1
,2
]}

Huy Phan, Anh ^{[1
]}

Asante-Mensah, Maame G. ^{[1
]}

Musavian Ghazani, Mirfarid ^{[1
]}

Tanaka, Toshihisa ^{[3
]}

Oseledets, Ivan ^{[1
]}

机构：

[1] Skolkovo Inst Sci & Technol SKOLTECH, CDISE, Moscow, Russia

[2] Nicolaus Copernicus Univ, PL-87100 Torun, Poland

[3] Tokyo Univ Agr & Technol, Tokyo, Japan

来源：

MACHINE LEARNING-SCIENCE AND TECHNOLOGY | 2021年 / 2卷 / 01期

关键词：

Tensor Ring-Tensor Train (TR-TT) decompositions; randomized algorithm; random projection; MATRIX PRODUCT STATES; LARGE-SCALE MATRICES; RENORMALIZATION-GROUP; APPROXIMATION; DECOMPOSITION; OPTIMIZATION; COMPLETION; NETWORKS; REDUCTION;

D O I：

10.1088/2632-2153/abad87

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Randomized algorithms are efficient techniques for big data tensor analysis. In this tutorial paper, we review and extend a variety of randomized algorithms for decomposing large-scale data tensors in Tensor Ring (TR) format. We discuss both adaptive and nonadaptive randomized algorithms for this task. Our main focus is on the random projection technique as an efficient randomized framework and how it can be used to decompose large-scale data tensors in the TR format. Simulations are provided to support the presentation and efficiency, and performance of the presented algorithms are compared.

引用

页数：21

共 50 条

[1] Fast and Accurate Randomized Algorithms for Low-rank Tensor Decompositions
Ma, Linjian
Solomonik, Edgar
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 34 (NEURIPS 2021), 2021, 34
[2] Randomized Algorithms for Low-Rank Tensor Decompositions in the Tucker Format
Minster, Rachel
Saibaba, Arvind K.
Kilmer, Misha E.
SIAM JOURNAL ON MATHEMATICS OF DATA SCIENCE, 2020, 2 (01): : 189 - 215
[3] Fast randomized tensor singular value thresholding for low-rank tensor optimization
Che, Maolin
Wang, Xuezhong
Wei, Yimin
Zhao, Xile
NUMERICAL LINEAR ALGEBRA WITH APPLICATIONS, 2022, 29 (06)
[4] Parallel Implementation of Fast Randomized Algorithms for Low Rank Matrix Decomposition
Lucas, Andrew
Stalzer, Mark
Feo, John
PARALLEL PROCESSING LETTERS, 2014, 24 (01)
[5] Efficient Low Rank Tensor Ring Completion
Wang, Wenqi
Aggarwal, Vaneet
Aeron, Shuchin
2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2017, : 5698 - 5706
[6] LOW-RANK TENSOR RING MODEL FOR COMPLETING MISSING VISUAL DATA
Asif, M. Salman
Prater-Bennette, Ashley
2020 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2020, : 5415 - 5419
[7] Noisy Tensor Completion via Low-Rank Tensor Ring
Qiu, Yuning
Zhou, Guoxu
Zhao, Qibin
Xie, Shengli
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2024, 35 (01) : 1127 - 1141
[8] Fast hypergraph regularized nonnegative tensor ring decomposition based on low-rank approximation
Zhao, Xinhai
Yu, Yuyuan
Zhou, Guoxu
Zhao, Qibin
Sun, Weijun
APPLIED INTELLIGENCE, 2022, 52 (15) : 17684 - 17707
[9] Fast nonnegative tensor ring decomposition based on the modulus method and low-rank approximation
YuYuan Yu
Kan Xie
JinShi Yu
Qi Jiang
ShengLi Xie
Science China Technological Sciences, 2021, 64 : 1843 - 1853
[10] Fast nonnegative tensor ring decomposition based on the modulus method and low-rank approximation
Yu YuYuan
Xie Kan
Yu JinShi
Jiang Qi
Xie ShengLi
SCIENCE CHINA-TECHNOLOGICAL SCIENCES, 2021, 64 (09) : 1843 - 1853

← 1 2 3 4 5 →