Smoothing fast proximal gradient algorithm for the relaxation of matrix rank regularization problem

This paper proposes a general inertial smoothing proximal gradient algorithm for solving the Capped-ℓ1 exact continuous relaxation regularization model proposed by Yu and Zhang (2022) [29]. The proposed algorithm incorporates different extrapolations into the gradient and proximal steps. It is prove...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Applied numerical mathematics Ročník 190; s. 303 - 320
Hlavní autoři:	Zhang, Jie, Yang, Xinmin
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Elsevier B.V 01.08.2023
Témata:	Convex nonsmooth loss function Inertial proximal gradient algorithm Matrix rank regularization problem Smoothing approximation Smoothing approximation Inertial proximal gradient algorithm Convex nonsmooth loss function Matrix rank regularization problem
ISSN:	0168-9274, 1873-5460
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	This paper proposes a general inertial smoothing proximal gradient algorithm for solving the Capped-ℓ1 exact continuous relaxation regularization model proposed by Yu and Zhang (2022) [29]. The proposed algorithm incorporates different extrapolations into the gradient and proximal steps. It is proved that, under some general parameter constraints, the singular values of any accumulation point of the sequence generated by the proposed algorithm have the common support set, and the zero singular values can be achieved in a finite number of iterations. Furthermore, any accumulation point is a lifted stationary point of the relaxation model. Numerical experiments illustrate the efficiency of the proposed algorithm on synthetic and real data, respectively.
ISSN:	0168-9274 1873-5460
DOI:	10.1016/j.apnum.2023.05.003