Generalized Nonconvex Nonsmooth Low-Rank Matrix Recovery Framework With Feasible Algorithm Designs and Convergence Analysis

Decomposing data matrix into low-rank plus additive matrices is a commonly used strategy in pattern recognition and machine learning. This article mainly studies the alternating direction method of multiplier (ADMM) with two dual variables, which is used to optimize the generalized nonconvex nonsmoo...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE transaction on neural networks and learning systems Ročník 34; číslo 9; s. 5342 - 5353
Hlavní autoři:	Zhang, Hengmin, Qian, Feng, Shi, Peng, Du, Wenli, Tang, Yang, Qian, Jianjun, Gong, Chen, Yang, Jian
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Piscataway IEEE 01.09.2023 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	Algorithm designs Algorithms Clustering Convergence convergence analysis Convex functions Critical point Learning systems Linear programming low-rank matrix recovery Machine learning Mathematical models Matrix decomposition Minimization multiple variables nonconvex alternating direction method of multiplier (ADMM) Objective function Optimization Pattern recognition Theoretical analysis
ISSN:	2162-237X, 2162-2388, 2162-2388
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Buďte první, kdo okomentuje tento záznam!