Efficient Parallel Algorithms for Linear RankSVM on GPU - Network and Parallel Computing
Conference Papers Year : 2014

Efficient Parallel Algorithms for Linear RankSVM on GPU

Jing Jin
  • Function : Author
  • PersonId : 994334
Xiaola Lin
  • Function : Author
  • PersonId : 994335

Abstract

Linear RankSVM is one of the widely used methods for learning to rank. Although using Order-Statistic Tree (OST) and Trust Region Newton Methods (TRON) are effective to train linear RankSVM on CPU, it becomes less effective when dealing with large-scale training data sets. Furthermore, linear RankSVM training with L2-loss contains quite amount of matrix manipulations in comparison with that with L1-loss, so it has great potential for achieving parallelism on GPU. In this paper, we design efficient parallel algorithms on GPU for the linear RankSVM training with L2-loss based on different queries. The experimental results show that, compared with the state-of-the-art algorithms for the linear RankSVM training with L2-loss on CPU, our proposed parallel algorithm not only can significantly enhance the training speed but also maintain the high prediction accuracy.
Fichier principal
Vignette du fichier
978-3-662-44917-2_16_Chapter.pdf (271.12 Ko) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-01403083 , version 1 (25-11-2016)

Licence

Identifiers

Cite

Jing Jin, Xiaola Lin. Efficient Parallel Algorithms for Linear RankSVM on GPU. 11th IFIP International Conference on Network and Parallel Computing (NPC), Sep 2014, Ilan, Taiwan. pp.181-194, ⟨10.1007/978-3-662-44917-2_16⟩. ⟨hal-01403083⟩
65 View
135 Download

Altmetric

Share

More