Stagewise Training With Exponentially Growing Training Sets

In the world of big data, training large-scale machine learning problems has gained considerable attention. Numerous innovative optimization strategies have been presented in recent years to accelerate the large-scale training process. However, the possibility of further accelerating the training pr...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transaction on neural networks and learning systems 2024-05, Vol.PP, p.1-11
Hauptverfasser:	Gu, Bin, AlQuabeh, Hilal, de Vazelhes, William, Huo, Zhouyuan, Huang, Heng
Format:	Artikel
Sprache:	eng
Schlagworte:	Approximation algorithms Computational complexity Gradient hard thresholding (GHT) algorithms Optimization proximal algorithms Risk minimization stagewise training strategy stochastic optimization Training Training data Upper bound
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!