Efficient parallel algorithm for nonlinear dimensionality reduction on GPU

Tsung Tai Yeh, Tseng Yi Chen, Yen Chiu Chen, Wei Kuan Shih

研究成果: 書貢獻/報告類型會議論文篇章同行評審

8 引文 斯高帕斯(Scopus)

摘要

Advances in nonlinear dimensionality reduction provide a way to understand and visualize the underlying structure of complex data sets. The performance of large-scale nonlinear dimensionality reduction is of key importance in data mining, machine learning, and data analysis. In this paper, we concentrate on improving the performance of nonlinear dimensionality reduction using large-scale data sets on the GPU. In particular, we focus on solving problems including k nearest neighbor (KNN) search and sparse spectral decomposition for large-scale data, and propose an efficient framework for Local Linear Embedding (LLE). We implement a k-d tree based KNN algorithm and Krylov subspace method on the GPU to accelerate the nonlinear dimensionality reduction for large-scale data. Our results enable GPU-based k-d tree LLE processes of up to about 30-60 X faster compared to the brute force KNN [10] LLE model on the CPU. Overall, our methods save O (n2-6n-2k-3) memory space.

原文???core.languages.en_GB???
主出版物標題Proceedings - 2010 IEEE International Conference on Granular Computing, GrC 2010
頁面592-597
頁數6
DOIs
出版狀態已出版 - 2010
事件2010 IEEE International Conference on Granular Computing, GrC 2010 - San Jose, CA, United States
持續時間: 14 8月 201016 8月 2010

出版系列

名字Proceedings - 2010 IEEE International Conference on Granular Computing, GrC 2010

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???2010 IEEE International Conference on Granular Computing, GrC 2010
國家/地區United States
城市San Jose, CA
期間14/08/1016/08/10

指紋

深入研究「Efficient parallel algorithm for nonlinear dimensionality reduction on GPU」主題。共同形成了獨特的指紋。

引用此