5711

Fast On-line Statistical Learning on a GPGPU

FangZhou Xiao, Eric McCreath, Christfried Webers
School of Computer Science, College of Engineering & Computer Science, The Australian National University, Canberra, ACT 0200, Australia
9th Australasian Symposium on Parallel and Distributed Computing, 2011

@article{xiao2011fast,

   title={Fast On-line Statistical Learning on a GPGPU},

   author={Xiao, F.Z. and McCreath, E. and Webers, C.},

   journal={Parallel and Distributed Computing 2011},

   volume={11},

   pages={35},

   year={2011}

}

Download Download (PDF)   View View   Source Source   

1481

views

On-line Machine Learning using Stochastic Gradient Descent is an inherently sequential computation. This makes it difficult to improve performance by simply employing parallel architectures. Langford et al. made a modification to the standard stochastic gradient descent approach which opens up the possibility of parallel computation. They also proved that there is no significant loss in accuracy in their approach. They did empirically demonstrate the performance gain in speed for the case of a pipelined architecture with a few processing units. In this paper we report on applying the Langford et al. approach on a General Purpose Graphics Processing Unit (GPGPU) with a large number of processing units. We accelerate the learning speed by approximately 4.5 times compared to a standard single threaded approach with comparable accuracy. We also evaluate the GPU performance for the sequential variant of the algorithm, which has not previously been reported. Finally, we investigate how changes in the number of threads, number of blocks, and amount of delay, effects the overall performance and accuracy.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2017 hgpu.org

All rights belong to the respective authors

Contact us: