Gaussian Process Models with Parallelization and GPU acceleration

Zhenwen Dai; Andreas Damianou; James Hensman; Neil D. Lawrence

edit

Back to publications

Gaussian Process Models with Parallelization and GPU acceleration

Zhenwen Dai, Andreas Damianou, James Hensman, Neil D. Lawrence

, 2014.

Abstract

In this work, we present an extension of Gaussian process (GP) models with sophisticated parallelization and GPU acceleration. The parallelization scheme arises naturally from the modular computational structure w.r.t. datapoints in the sparse Gaussian process formulation. Additionally, the computational bottleneck is implemented with GPU acceleration for further speed up. Combining both techniques allows applying Gaussian process models to millions of datapoints. The efficiency of our algorithm is demonstrated with a synthetic dataset. Its source code has been integrated into our popular software library GPy.

Links

Cite this Paper

BibTeX


@Misc{Dai-gpu14,
  title = 	 {Gaussian Process Models with Parallelization and {GPU} acceleration},
  author = 	 {Dai, Zhenwen and Damianou, Andreas and Hensman, James and Lawrence, Neil D.},
  year = 	 {2014},
  pdf = 	 {https://arxiv.org/pdf/1412.1370.pdf},
  url = 	 {/publications/dai-gpu14.html},
  abstract = 	 {In this work, we present an extension of Gaussian process (GP) models with sophisticated parallelization and GPU acceleration. The parallelization scheme  arises naturally from the modular computational structure w.r.t. datapoints in the sparse Gaussian process formulation. Additionally, the computational bottleneck is implemented with GPU acceleration for further speed up. Combining both techniques allows applying Gaussian process models to millions of datapoints. The efficiency of our algorithm is demonstrated with a synthetic dataset. Its source code has been integrated into our popular software library GPy.
}
}

Endnote

%0 Generic
%T Gaussian Process Models with Parallelization and GPU acceleration
%A Zhenwen Dai
%A Andreas Damianou
%A James Hensman
%A Neil D. Lawrence
%D 2014	
%F Dai-gpu14
%U /publications/dai-gpu14.html
%X In this work, we present an extension of Gaussian process (GP) models with sophisticated parallelization and GPU acceleration. The parallelization scheme  arises naturally from the modular computational structure w.r.t. datapoints in the sparse Gaussian process formulation. Additionally, the computational bottleneck is implemented with GPU acceleration for further speed up. Combining both techniques allows applying Gaussian process models to millions of datapoints. The efficiency of our algorithm is demonstrated with a synthetic dataset. Its source code has been integrated into our popular software library GPy.

RIS


TY  - GEN
TI  - Gaussian Process Models with Parallelization and GPU acceleration
AU  - Zhenwen Dai
AU  - Andreas Damianou
AU  - James Hensman
AU  - Neil D. Lawrence
DA  - 2014/10/18	
ID  - Dai-gpu14
L1  - https://arxiv.org/pdf/1412.1370.pdf
UR  - /publications/dai-gpu14.html
AB  - In this work, we present an extension of Gaussian process (GP) models with sophisticated parallelization and GPU acceleration. The parallelization scheme  arises naturally from the modular computational structure w.r.t. datapoints in the sparse Gaussian process formulation. Additionally, the computational bottleneck is implemented with GPU acceleration for further speed up. Combining both techniques allows applying Gaussian process models to millions of datapoints. The efficiency of our algorithm is demonstrated with a synthetic dataset. Its source code has been integrated into our popular software library GPy.

ER  -

APA


Dai, Z., Damianou, A., Hensman, J. & Lawrence, N.D.. (2014). Gaussian Process Models with Parallelization and GPU acceleration.  Available from /publications/dai-gpu14.html.