Fully Projection-Free Proximal Stochastic Gradient Method With Optimal Convergence Rates

Proximal stochastic gradient plays an important role in large-scale machine learning and big data analysis. It needs to iteratively update models within a feasible set until convergence. The computational cost is usually high due to the projection over the feasible set. To reduce complexity, many pr...

Ausführliche Beschreibung

Bibliografische Detailangaben

Hauptverfasser:	Yan Li, Xiaofeng Cao, Honghui Chen
Format:	Artigo
Sprache:	Inglês
Veröffentlicht:	IEEE 2020-01-01
Schriftenreihe:	IEEE Access
Schlagworte:	Proximal stochastic gradient projection-free optimization convergence optimization
Online-Zugang:	https://ieeexplore.ieee.org/document/9178808/
Tags:	Tag hinzufügen Keine Tags, Fügen Sie das erste Tag hinzu!