Novel Alternating Least Squares Algorithm for Nonnegative Matrix and Tensor Factorizations

被引：0

作者：

Anh Huy Phan ^{[1
]}

Cichocki, Andrzej ^{[1
]}

Zdunek, Rafal ^{[1
,2
]}

Thanh Vu Dinh ^{[3
]}

机构：

[1] RIKEN, Lab Adv Brain Signal Proc, Brain Sci Inst, 2-1 Hirosawa, Wako, Saitama 3510198, Japan

[2] Teleinformat Acoust, Inst Telecommun, Wroclaw, Poland

[3] HoChiMinh City Univ Technol, Vietnam, Vietnam

来源：

NEURAL INFORMATION PROCESSING: THEORY AND ALGORITHMS, PT I | 2010年 / 6443卷

关键词：

RARAFAC; nonnegative tensor factorization; NMF; nonnegative quadratic programming; parallel computing; ALS; object classification;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Alternative least squares (ALS) algorithm is considered as a "work-horse" algorithm for general tensor factorizations. For nonnegative tensor factorizations (NTF), we usually use a nonlinear projection (rectifier) to remove negative entries during the iteration process. However, this kind of ALS algorithm often fails and cannot converge to the desired solution. In this paper, we proposed a novel algorithm for NTF by recursively solving nonnegative quadratic programming problems. The validity and high performance of the proposed algorithm has been confirmed for difficult benchmarks, and also in an application of object classification.

引用

页码：262 / +

页数：2

共 50 条

[1] Seeking an appropriate alternative least squares algorithm for nonnegative tensor factorizations
Anh Huy Phan
Cichocki, Andrzej
[J]. NEURAL COMPUTING & APPLICATIONS, 2012, 21 (04): : 623 - 637
[2] A framework for least squares nonnegative matrix factorizations with Tikhonov regularization
Teng, Yueyang
Qi, Shouliang
Han, Fangfang
Yao, Yudong
Fan, Fenglei
Lyu, Qing
Wang, Ge
[J]. NEUROCOMPUTING, 2020, 387 : 78 - 90
[3] Convergence of a Fast Hierarchical Alternating Least Squares Algorithm for Nonnegative Matrix Factorization
Hou, Liangshao
Chu, Delin
Liao, Li-Zhi
[J]. IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2024, 36 (01) : 77 - 89
[4] Hybrid projective nonnegative matrix factorization based on α-divergence and the alternating least squares algorithm
Belachew, Melisew Tefera
Del Buono, Nicoletta
[J]. APPLIED MATHEMATICS AND COMPUTATION, 2020, 369
[5] An efficient algorithm for solving the nonnegative tensor least squares problem
Duan, Xue-Feng
Duan, Shan-Qi
Li, Juan
Li, Jiao-fen
Wang, Qing-Wen
[J]. NUMERICAL LINEAR ALGEBRA WITH APPLICATIONS, 2021, 28 (06)
[6] Distributed geometric nonnegative matrix factorization and hierarchical alternating least squares-based nonnegative tensor factorization with the MapReduce paradigm
Zdunek, Rafal
Fonal, Krzysztof
[J]. CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE, 2018, 30 (17):
[7] Nonnegative tensor factorizations using an alternating direction method
Cai, Xingju
Chen, Yannan
Han, Deren
[J]. FRONTIERS OF MATHEMATICS IN CHINA, 2013, 8 (01) : 3 - 18
[8] Nonnegative tensor factorizations using an alternating direction method
Xingju Cai
Yannan Chen
Deren Han
[J]. Frontiers of Mathematics in China, 2013, 8 : 3 - 18
[9] Nonnegative Matrix and Tensor Factorizations [An algorithmic perspective]
Zhou, Guoxu
Cichocki, Andrzej
Zhao, Qibin
Xie, Shengli
[J]. IEEE SIGNAL PROCESSING MAGAZINE, 2014, 31 (03) : 54 - 65
[10] AN ALTERNATING RANK-k NONNEGATIVE LEAST SQUARES FRAMEWORK (ARkNLS) FOR NONNEGATIVE MATRIX FACTORIZATION
Chu, Delin
Shi, Weya
Eswar, Srinivas
Park, Haesun
[J]. SIAM JOURNAL ON MATRIX ANALYSIS AND APPLICATIONS, 2021, 42 (04) : 1451 - 1479

← 1 2 3 4 5 →