Parallelizable sparse inverse formulation Gaussian processes (SpInGP)

Alexander Grigorievskiy; Neil Lawrence; Simo Särkkä

edit

Back to publications

Parallelizable sparse inverse formulation Gaussian processes (SpInGP)

Alexander Grigorievskiy, Neil Lawrence, Simo Särkkä

, 2016.

Abstract

We propose a parallelizable sparse inverse formulation Gaussian process (SpInGP) for temporal models. It uses a sparse precision GP formulation and sparse matrix routines to speed up the computations. Due to the state-space formulation used in the algorithm, the time complexity of the basic SpInGP is linear, and because all the computations are parallelizable, the parallel form of the algorithm is sublinear in the number of data points. We provide example algorithms to implement the sparse matrix routines and experimentally test the method using both simulated and real data.

Links

Cite this Paper

BibTeX


@Misc{parallelizable-sparse-inverse-formulation-gaussian-processes-spingp,
  title = 	 {Parallelizable sparse inverse formulation Gaussian processes (SpInGP)},
  author = 	 {Grigorievskiy, Alexander and Lawrence, Neil and Särkkä, Simo},
  year = 	 {2016},
  url = 	 {/publications/parallelizable-sparse-inverse-formulation-gaussian-processes-spingp.html},
  abstract = 	 {We propose a parallelizable sparse inverse formulation Gaussian process (SpInGP) for temporal models. It uses a sparse precision GP formulation and sparse matrix routines to speed up the computations. Due to the state-space formulation used in the algorithm, the time complexity of the basic SpInGP is linear, and because all the computations are parallelizable, the parallel form of the algorithm is sublinear in the number of data points. We provide example algorithms to implement the sparse matrix routines and experimentally test the method using both simulated and real data.
}
}

Endnote

%0 Generic
%T Parallelizable sparse inverse formulation Gaussian processes (SpInGP)
%A Alexander Grigorievskiy
%A Neil Lawrence
%A Simo Särkkä
%D 2016	
%F parallelizable-sparse-inverse-formulation-gaussian-processes-spingp
%U /publications/parallelizable-sparse-inverse-formulation-gaussian-processes-spingp.html
%X We propose a parallelizable sparse inverse formulation Gaussian process (SpInGP) for temporal models. It uses a sparse precision GP formulation and sparse matrix routines to speed up the computations. Due to the state-space formulation used in the algorithm, the time complexity of the basic SpInGP is linear, and because all the computations are parallelizable, the parallel form of the algorithm is sublinear in the number of data points. We provide example algorithms to implement the sparse matrix routines and experimentally test the method using both simulated and real data.

RIS


TY  - GEN
TI  - Parallelizable sparse inverse formulation Gaussian processes (SpInGP)
AU  - Alexander Grigorievskiy
AU  - Neil Lawrence
AU  - Simo Särkkä
DA  - 2016/10/25	
ID  - parallelizable-sparse-inverse-formulation-gaussian-processes-spingp
UR  - /publications/parallelizable-sparse-inverse-formulation-gaussian-processes-spingp.html
AB  - We propose a parallelizable sparse inverse formulation Gaussian process (SpInGP) for temporal models. It uses a sparse precision GP formulation and sparse matrix routines to speed up the computations. Due to the state-space formulation used in the algorithm, the time complexity of the basic SpInGP is linear, and because all the computations are parallelizable, the parallel form of the algorithm is sublinear in the number of data points. We provide example algorithms to implement the sparse matrix routines and experimentally test the method using both simulated and real data.

ER  -

APA


Grigorievskiy, A., Lawrence, N. & Särkkä, S.. (2016). Parallelizable sparse inverse formulation Gaussian processes (SpInGP).  Available from /publications/parallelizable-sparse-inverse-formulation-gaussian-processes-spingp.html.