OPAC (Online Public Access Catalog)
Pencarian Koleksi UPA Perpustakaan
start it by typing one or more keywords for title, author or subject
Extragradient Method in Optimization: Convergence and Complexity
NGUYEN, Trong Phong - Personal Name
We consider the extragradient method to minimize the sum of two functions, the first one being smooth and the second being convex. Under the Kurdyka–
Łojasiewicz assumption, we prove that the sequence produced by the extragradient method converges to a critical point of the problem and has finite length. The analysis is extended to the case when both functions are convex. We provide, in this case, a sublinear convergence rate, as for gradient-based methods. Furthermore, we show that the recent small-prox complexity result can be applied to this method. Considering the extragradient method is an occasion to describe an exact line search scheme for proximal decomposition methods. We provide details for the implementation of this scheme for the one-norm regularized least squares problem and demonstrate numerical results which suggest that combining nonaccelerated methods with exact line search can be a competitive choice.
Łojasiewicz assumption, we prove that the sequence produced by the extragradient method converges to a critical point of the problem and has finite length. The analysis is extended to the case when both functions are convex. We provide, in this case, a sublinear convergence rate, as for gradient-based methods. Furthermore, we show that the recent small-prox complexity result can be applied to this method. Considering the extragradient method is an occasion to describe an exact line search scheme for proximal decomposition methods. We provide details for the implementation of this scheme for the one-norm regularized least squares problem and demonstrate numerical results which suggest that combining nonaccelerated methods with exact line search can be a competitive choice.
Availability
| EB00000003452K | Available |
Detail Information
Series Title
-
Call Number
-
Publisher
: ,
Collation
-
Language
ISBN/ISSN
-
Classification
NONE
Detail Information
Content Type
E-Jurnal
Media Type
-
Carrier Type
-
Edition
-
Subject(s)
Extragradient
Descent method
Forward–Backward splitting
Kurdyka–Łojasiewicz inequality
Complexity, first-order method
LASSO problem
Specific Detail Info
-
Statement of Responsibility
Trong Phong Nguyen ...[et al]
No other version available
File Attachment
