Stochastic DCA for minimizing a large sum of DC functions with application to multi-class logistic regression - Université de Lorraine
Journal Articles Neural Networks Year : 2020

Stochastic DCA for minimizing a large sum of DC functions with application to multi-class logistic regression

Abstract

We consider the large sum of DC (Difference of Convex) functions minimization problem which appear in several different areas, especially in stochastic optimization and machine learning. Two DCA (DC Algorithm) based algorithms are proposed: stochastic DCA and inexact stochastic DCA. We prove that the convergence of both algorithms to a critical point is guaranteed with probability one. Furthermore, we develop our stochastic DCA for solving an important problem in multi-task learning, namely group variables selection in multi class logistic regression. The corresponding stochastic DCA is very inexpensive, all computations are explicit. Numerical experiments on several benchmark datasets and synthetic datasets illustrate the efficiency of our algorithms and their superiority over existing methods, with respect to classification accuracy, sparsity of solution as well as running time.
Fichier principal
Vignette du fichier
S0893608020303233.pdf (301.35 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03063833 , version 1 (14-09-2022)

Licence

Identifiers

Cite

Hoai An Le Thi, Hoai Minh Le, Duy Nhat Phan, Bach Tran. Stochastic DCA for minimizing a large sum of DC functions with application to multi-class logistic regression. Neural Networks, 2020, 132, pp.220-231. ⟨10.1016/j.neunet.2020.08.024⟩. ⟨hal-03063833⟩
118 View
60 Download

Altmetric

Share

More