Online Stochastic DCA With Applications to Principal Component Analysis - Université de Lorraine Accéder directement au contenu
Article Dans Une Revue IEEE Transactions on Neural Networks and Learning Systems Année : 2022

Online Stochastic DCA With Applications to Principal Component Analysis

Résumé

Stochastic algorithms are well-known for their performance in the era of big data. In this article, we study nonsmooth stochastic Difference-of-Convex functions (DC) programs—the major class of nonconvex stochastic optimization, which have a variety of applications in divers domains, in particular, machine learning. We propose new online stochastic algorithms based on the state-of-the-art DC Algorithm (DCA)—a powerful approach in nonconvex programming framework, in the online context of streaming data continuously generated by some (unknown) source distribution. The new schemes use the stochastic approximations (SAs) principle: deterministic quantities of the standard DCA are replaced by their noisy estimators constructed using newly arriving samples. The convergence analysis of the proposed algorithms is studied intensively with the help of tools from modern convex analysis and martingale theory. Finally, we study several aspects of the proposed algorithms on an important problem in machine learning: the expected problem in principal component analysis (PCA).

Dates et versions

hal-04003755 , version 1 (24-02-2023)

Identifiants

Citer

Hoai an Le Thi, Hoang Phuc Hau Luu, Tao Pham Dinh. Online Stochastic DCA With Applications to Principal Component Analysis. IEEE Transactions on Neural Networks and Learning Systems, 2022, ⟨10.1109/TNNLS.2022.3213558⟩. ⟨hal-04003755⟩
24 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More