New Douglas-Rashford Splitting Algorithms for Generalized DC Programming with Applications in Machine Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yao, Yonghong, Jolaoso, Lateef O., Shehu, Yekini, Yao, Jen-Chih
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916218763476992
author Yao, Yonghong
Jolaoso, Lateef O.
Shehu, Yekini
Yao, Jen-Chih
author_facet Yao, Yonghong
Jolaoso, Lateef O.
Shehu, Yekini
Yao, Jen-Chih
contents In this work, we propose some new Douglas-Rashford splitting algorithms for solving a class of generalized DC (difference of convex functions) in real Hilbert spaces. The proposed methods leverage the proximal properties of the nonsmooth component and a fasten control parameter which improves the convergence rate of the algorithms. We prove the convergence of these methods to the critical points of nonconvex optimization under reasonable conditions. We evaluate the performance and effectiveness of our methods through experimentation with three practical examples in machine learning. Our findings demonstrated that our methods offer efficiency in problem-solving and outperform state-of-the-art techniques like the DCA (DC Algorithm) and ADMM.
format Preprint
id arxiv_https___arxiv_org_abs_2404_14800
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle New Douglas-Rashford Splitting Algorithms for Generalized DC Programming with Applications in Machine Learning
Yao, Yonghong
Jolaoso, Lateef O.
Shehu, Yekini
Yao, Jen-Chih
Optimization and Control
In this work, we propose some new Douglas-Rashford splitting algorithms for solving a class of generalized DC (difference of convex functions) in real Hilbert spaces. The proposed methods leverage the proximal properties of the nonsmooth component and a fasten control parameter which improves the convergence rate of the algorithms. We prove the convergence of these methods to the critical points of nonconvex optimization under reasonable conditions. We evaluate the performance and effectiveness of our methods through experimentation with three practical examples in machine learning. Our findings demonstrated that our methods offer efficiency in problem-solving and outperform state-of-the-art techniques like the DCA (DC Algorithm) and ADMM.
title New Douglas-Rashford Splitting Algorithms for Generalized DC Programming with Applications in Machine Learning
topic Optimization and Control
url https://arxiv.org/abs/2404.14800