Gaussian process learning from order relationships using expectation propagation

Ruixuan Wang; Stephen J. McKenna

doi:10.1109/ICPR.2010.153

Gaussian process learning from order relationships using expectation propagation

Research output: Chapter in Book/Report/Conference proceeding › Other chapter contribution

Abstract

A method for Gaussian process learning of a scalar function from a set of pair-wise order relationships is presented. Expectation propagation is used to obtain an approximation to the log marginal likelihood which is optimised using an analytical expression for its gradient. Experimental results show that the proposed method performs well compared with a previous method for Gaussian process preference learning.

Original language	English
Title of host publication	Proceedings - International Conference on Pattern Recognition
Pages	605-608
Number of pages	4
DOIs	https://doi.org/10.1109/ICPR.2010.153
Publication status	Published - 2010
Event	20th International Conference on Pattern Recognition - Istanbul, Turkey Duration: 23 Aug 2010 → 26 Aug 2010

Conference

Conference	20th International Conference on Pattern Recognition
Abbreviated title	ICPR 2010
Country	Turkey
City	Istanbul
Period	23/08/10 → 26/08/10

Keywords

Analytical expressions
Expectation propagation
Gaussian processes
Marginal likelihood
Preference learning
Scalar function
Gaussian noise (electronic)
Pattern recognition
Gaussian distribution

Access to Document

10.1109/ICPR.2010.153

Link to publication in Scopus

Fingerprint Dive into the research topics of 'Gaussian process learning from order relationships using expectation propagation'. Together they form a unique fingerprint.

Cite this

@inbook{8b5106ca7bf548dd85de536fac900681,

title = "Gaussian process learning from order relationships using expectation propagation",

abstract = "A method for Gaussian process learning of a scalar function from a set of pair-wise order relationships is presented. Expectation propagation is used to obtain an approximation to the log marginal likelihood which is optimised using an analytical expression for its gradient. Experimental results show that the proposed method performs well compared with a previous method for Gaussian process preference learning.",

keywords = "Analytical expressions, Expectation propagation, Gaussian processes, Marginal likelihood, Preference learning, Scalar function, Gaussian noise (electronic), Pattern recognition, Gaussian distribution",

author = "Ruixuan Wang and McKenna, {Stephen J.}",

year = "2010",

doi = "10.1109/ICPR.2010.153",

language = "English",

isbn = "9781424475421",

pages = "605--608",

booktitle = "Proceedings - International Conference on Pattern Recognition",

note = "20th International Conference on Pattern Recognition, ICPR 2010 ; Conference date: 23-08-2010 Through 26-08-2010",

}

TY - CHAP

T1 - Gaussian process learning from order relationships using expectation propagation

AU - Wang, Ruixuan

AU - McKenna, Stephen J.

PY - 2010

Y1 - 2010

N2 - A method for Gaussian process learning of a scalar function from a set of pair-wise order relationships is presented. Expectation propagation is used to obtain an approximation to the log marginal likelihood which is optimised using an analytical expression for its gradient. Experimental results show that the proposed method performs well compared with a previous method for Gaussian process preference learning.

AB - A method for Gaussian process learning of a scalar function from a set of pair-wise order relationships is presented. Expectation propagation is used to obtain an approximation to the log marginal likelihood which is optimised using an analytical expression for its gradient. Experimental results show that the proposed method performs well compared with a previous method for Gaussian process preference learning.

KW - Analytical expressions

KW - Expectation propagation

KW - Gaussian processes

KW - Marginal likelihood

KW - Preference learning

KW - Scalar function

KW - Gaussian noise (electronic)

KW - Pattern recognition

KW - Gaussian distribution

UR - http://www.scopus.com/inward/record.url?scp=78149476283&partnerID=8YFLogxK

U2 - 10.1109/ICPR.2010.153

DO - 10.1109/ICPR.2010.153

M3 - Other chapter contribution

AN - SCOPUS:78149476283

SN - 9781424475421

SP - 605

EP - 608

BT - Proceedings - International Conference on Pattern Recognition

T2 - 20th International Conference on Pattern Recognition

Y2 - 23 August 2010 through 26 August 2010

ER -