Novel DCA based algorithms for a special class of nonconvex problems with application in machine learning - Université de Lorraine Access content directly
Journal Articles Applied Mathematics and Computation Year : 2021

Novel DCA based algorithms for a special class of nonconvex problems with application in machine learning

Abstract

We address the problem of minimizing the sum of a nonconvex, differentiable function and composite functions by DC (Difference of Convex functions) programming and DCA (DC Algorithm), powerful tools of nonconvex optimization. The main idea of DCA relies on DC decompositions of the objective function, it consists in approximating a DC (nonconvex) program by a sequence of convex ones. We first develop a standard DCA scheme especially dealing with the very specific structure of this problem. Furthermore, we extend DCA to give rise to the so-named DCA-Like, which is based on a new and efficient way to approximate the DC objective function without knowing a DC decomposition. We further improve DCA based algorithms by incorporating the Nesterov’s acceleration technique into them. The convergence properties and the convergence rate under Kurdyka-Łojasiewicz assumption of extended DCAs are rigorously studied. We prove that DCA-Like and the accelerated versions subsequently converge from every initial point to a critical point of the considered problem. Finally, we investigate the proposed algorithms for an important problem in machine learning: the t-distributed stochastic neighbor embedding. Numerical experiments on several benchmark datasets illustrate the efficiency of our algorithms.
Fichier principal
Vignette du fichier
S0096300320308572.pdf (13.39 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03565125 , version 1 (02-08-2023)

Licence

Attribution - NonCommercial

Identifiers

Cite

Hoai An Le Thi, Hoai Minh Le, Duy Nhat Phan, Bach Tran. Novel DCA based algorithms for a special class of nonconvex problems with application in machine learning. Applied Mathematics and Computation, 2021, 409, pp.125904. ⟨10.1016/j.amc.2020.125904⟩. ⟨hal-03565125⟩
87 View
1 Download

Altmetric

Share

Gmail Facebook X LinkedIn More