Parallelizable sparse inverse formulation Gaussian processes (SpInGP)

Alexander Grigorevskiy; Neil Lawrence; Simo Särkkä

doi:10.1109/MLSP.2017.8168130

Parallelizable sparse inverse formulation Gaussian processes (SpInGP)

Alexander Grigorevskiy, Neil Lawrence, Simo Särkkä

Univ Sheffield, University of Sheffield, Dept Chem & Biol Engn

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussa › Conference article in proceedings › Scientific › vertaisarvioitu

13 Sitaatiot (Scopus)

Abstrakti

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.

Alkuperäiskieli	Englanti
Otsikko	2017 IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2017 - Proceedings
Kustantaja	IEEE
Sivumäärä	7
ISBN (painettu)	978-1-5090-6341-3
DOI - pysyväislinkit	https://doi.org/10.1109/MLSP.2017.8168130
Tila	Julkaistu - 2017
OKM-julkaisutyyppi	A4 Artikkeli konferenssijulkaisussa
Tapahtuma	IEEE International Workshop on Machine Learning for Signal Processing - Tokyo, Japani Kesto: 25 syysk. 2017 → 28 syysk. 2017 Konferenssinumero: 27 http://mlsp2017.conwiz.dk/home.htm

Julkaisusarja

Nimi	IEEE International Workshop on Machine Learning for Signal Processing
Kustantaja	IEEE
ISSN (painettu)	2161-0363
ISSN (elektroninen)	2161-0371

Workshop

Workshop	IEEE International Workshop on Machine Learning for Signal Processing
Lyhennettä	MLSP
Maa/Alue	Japani
Kaupunki	Tokyo
Ajanjakso	25/09/2017 → 28/09/2017
www-osoite	http://mlsp2017.conwiz.dk/home.htm

Pääsy asiakirjaan

10.1109/MLSP.2017.8168130

https://arxiv.org/abs/1610.08035

Siteeraa tätä

@inproceedings{55b4111592b84e34834f2ef9f20ee26f,

title = "Parallelizable sparse inverse formulation Gaussian processes (SpInGP)",

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. ",

author = "Alexander Grigorevskiy and Neil Lawrence and Simo S{\"a}rkk{\"a}",

year = "2017",

doi = "10.1109/MLSP.2017.8168130",

language = "English",

isbn = "978-1-5090-6341-3",

series = "IEEE International Workshop on Machine Learning for Signal Processing",

publisher = "IEEE",

booktitle = "2017 IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2017 - Proceedings",

address = "United States",

note = "IEEE International Workshop on Machine Learning for Signal Processing , MLSP ; Conference date: 25-09-2017 Through 28-09-2017",

url = "http://mlsp2017.conwiz.dk/home.htm",

}

Grigorevskiy, A, Lawrence, N & Särkkä, S 2017, Parallelizable sparse inverse formulation Gaussian processes (SpInGP). julkaisussa 2017 IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2017 - Proceedings. IEEE International Workshop on Machine Learning for Signal Processing, IEEE, IEEE International Workshop on Machine Learning for Signal Processing , Tokyo, Japani, 25/09/2017. https://doi.org/10.1109/MLSP.2017.8168130

Parallelizable sparse inverse formulation Gaussian processes (SpInGP). / Grigorevskiy, Alexander; Lawrence, Neil; Särkkä, Simo.
2017 IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2017 - Proceedings. IEEE, 2017. (IEEE International Workshop on Machine Learning for Signal Processing).

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussa › Conference article in proceedings › Scientific › vertaisarvioitu

TY - GEN

T1 - Parallelizable sparse inverse formulation Gaussian processes (SpInGP)

AU - Grigorevskiy, Alexander

AU - Lawrence, Neil

AU - Särkkä, Simo

N1 - Conference code: 27

PY - 2017

Y1 - 2017

N2 - 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.

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.

U2 - 10.1109/MLSP.2017.8168130

DO - 10.1109/MLSP.2017.8168130

M3 - Conference article in proceedings

SN - 978-1-5090-6341-3

T3 - IEEE International Workshop on Machine Learning for Signal Processing

BT - 2017 IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2017 - Proceedings

PB - IEEE

T2 - IEEE International Workshop on Machine Learning for Signal Processing

Y2 - 25 September 2017 through 28 September 2017

ER -

Parallelizable sparse inverse formulation Gaussian processes (SpInGP)

Abstrakti

Julkaisusarja

Workshop

Pääsy asiakirjaan

Sormenjälki

Siteeraa tätä