Incremental Delayed Subgradient Method for Decentralized Nonsmooth Convex–Concave Minimax Optimization

In this paper, we propose an incremental-type subgradient scheme for solving a nonsmooth convex–concave minimax optimization problem in the setting of Euclidean spaces. We investigate convergence results by deriving an upper bound for the absolute value of the difference between the function value o...

Full description

Saved in:
Bibliographic Details
Main Authors: Thipagon Feesantia, Tipsuda Arunrat, Nimit Nimana
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Algorithms
Subjects:
Online Access:https://www.mdpi.com/1999-4893/18/3/126
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849340753570955264
author Thipagon Feesantia
Tipsuda Arunrat
Nimit Nimana
author_facet Thipagon Feesantia
Tipsuda Arunrat
Nimit Nimana
author_sort Thipagon Feesantia
collection DOAJ
description In this paper, we propose an incremental-type subgradient scheme for solving a nonsmooth convex–concave minimax optimization problem in the setting of Euclidean spaces. We investigate convergence results by deriving an upper bound for the absolute value of the difference between the function value of the averaged iterates and the saddle value, provided that the step size is a constant. By assuming that the step-size sequence is diminishing, we prove the convergences of both the averaged sequence of function values and the sequence of function values of averaged iterates to the saddle value. Finally, we also show some numerical examples for illustrating the obtained theoretical result.
format Article
id doaj-art-88d548c931e14b9eb9cd72bb6a989be6
institution Kabale University
issn 1999-4893
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Algorithms
spelling doaj-art-88d548c931e14b9eb9cd72bb6a989be62025-08-20T03:43:50ZengMDPI AGAlgorithms1999-48932025-02-0118312610.3390/a18030126Incremental Delayed Subgradient Method for Decentralized Nonsmooth Convex–Concave Minimax OptimizationThipagon Feesantia0Tipsuda Arunrat1Nimit Nimana2Department of Mathematics, Faculty of Science, Khon Kaen University, Khon Kaen 40002, ThailandDepartment of Mathematics, Faculty of Science, Khon Kaen University, Khon Kaen 40002, ThailandDepartment of Mathematics, Faculty of Science, Khon Kaen University, Khon Kaen 40002, ThailandIn this paper, we propose an incremental-type subgradient scheme for solving a nonsmooth convex–concave minimax optimization problem in the setting of Euclidean spaces. We investigate convergence results by deriving an upper bound for the absolute value of the difference between the function value of the averaged iterates and the saddle value, provided that the step size is a constant. By assuming that the step-size sequence is diminishing, we prove the convergences of both the averaged sequence of function values and the sequence of function values of averaged iterates to the saddle value. Finally, we also show some numerical examples for illustrating the obtained theoretical result.https://www.mdpi.com/1999-4893/18/3/126delayincremental methodminimax problemsaddle pointsubgradient method
spellingShingle Thipagon Feesantia
Tipsuda Arunrat
Nimit Nimana
Incremental Delayed Subgradient Method for Decentralized Nonsmooth Convex–Concave Minimax Optimization
Algorithms
delay
incremental method
minimax problem
saddle point
subgradient method
title Incremental Delayed Subgradient Method for Decentralized Nonsmooth Convex–Concave Minimax Optimization
title_full Incremental Delayed Subgradient Method for Decentralized Nonsmooth Convex–Concave Minimax Optimization
title_fullStr Incremental Delayed Subgradient Method for Decentralized Nonsmooth Convex–Concave Minimax Optimization
title_full_unstemmed Incremental Delayed Subgradient Method for Decentralized Nonsmooth Convex–Concave Minimax Optimization
title_short Incremental Delayed Subgradient Method for Decentralized Nonsmooth Convex–Concave Minimax Optimization
title_sort incremental delayed subgradient method for decentralized nonsmooth convex concave minimax optimization
topic delay
incremental method
minimax problem
saddle point
subgradient method
url https://www.mdpi.com/1999-4893/18/3/126
work_keys_str_mv AT thipagonfeesantia incrementaldelayedsubgradientmethodfordecentralizednonsmoothconvexconcaveminimaxoptimization
AT tipsudaarunrat incrementaldelayedsubgradientmethodfordecentralizednonsmoothconvexconcaveminimaxoptimization
AT nimitnimana incrementaldelayedsubgradientmethodfordecentralizednonsmoothconvexconcaveminimaxoptimization