Scalable Task-Parallel SGD on Matrix Factorization in Multicore Architectures

Recommendation is an indispensable technique especially in e-commerce services such as Amazon or Netflix to provide more preferable items to users. Matrix factorization is a well-known algorithm for recommendation which estimates affinities between users and items solely based on ratings explicitly...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	2015 IEEE International Parallel and Distributed Processing Symposium Workshop S. 1178 - 1184
Hauptverfasser:	Nishioka, Yusuke, Taura, Kenjiro
Format:	Tagungsbericht
Sprache:	Englisch Japanisch
Veröffentlicht:	IEEE 01.05.2015
Schlagworte:	Convergence Instruction sets Load management Matrix factorization Radiation detectors Recommender systems Scalability Sparse matrices Stochastic gradient descent Synchronization Task parallel model
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!