New Douglas-Rashford Splitting Algorithms for Generalized DC Programming with Applications in Machine Learning: New Douglas-Rashford splitting algorithms for generalized DC programming with applications in machine learning

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος: New Douglas-Rashford Splitting Algorithms for Generalized DC Programming with Applications in Machine Learning: New Douglas-Rashford splitting algorithms for generalized DC programming with applications in machine learning
Συγγραφείς: Yonghong Yao, Lateef O. Jolaoso, Yekini Shehu, Jen-Chih Yao
Πηγή: Journal of Scientific Computing. 103
Publication Status: Preprint
Στοιχεία εκδότη: Springer Science and Business Media LLC, 2025.
Έτος έκδοσης: 2025
Θεματικοί όροι: machine learning, Numerical mathematical programming methods, DC programming, Nonlinear programming, Optimization and Control (math.OC), nonconvex optimization, Learning and adaptive systems in artificial intelligence, FOS: Mathematics, Nonconvex programming, global optimization, Douglas-Rachford splitting algorithm, Mathematics - Optimization and Control
Περιγραφή: 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.
Τύπος εγγράφου: Article
Περιγραφή αρχείου: application/xml
Γλώσσα: English
ISSN: 1573-7691
0885-7474
DOI: 10.1007/s10915-025-02900-6
DOI: 10.48550/arxiv.2404.14800
Σύνδεσμος πρόσβασης: http://arxiv.org/abs/2404.14800
Rights: Springer Nature TDM
CC BY
Αριθμός Καταχώρησης: edsair.doi.dedup.....1ad6a271c23c8b830f3e54ca845fdd9d
Βάση Δεδομένων: OpenAIRE