Markov chain Monte Carlo algorithms for Gaussian processes

[edit]

Michalis K. Titsias, University of Athens
Magnus Rattray, University of Manchester
Neil D. Lawrence, University of Sheffield

Chapter 14 in Bayesian Time Series Models

Abstract

’What’s going to happen next?’ Time series data hold the answers, and Bayesian methods represent the cutting edge in learning what they have to say. This ambitious book is the first unified treatment of the emerging knowledge-base in Bayesian time series techniques. Exploiting the unifying framework of probabilistic graphical models, the book covers approximation schemes, both Monte Carlo and deterministic, and introduces switching, multi-object, non-parametric and agent-based models in a variety of application environments. It demonstrates that the basic framework supports the rapid creation of models tailored to specific applications and gives insight into the computational complexity of their implementation. The authors span traditional disciplines such as statistics and engineering and the more recently established areas of machine learning and pattern recognition. Readers with a basic understanding of applied probability, but no experience with time series analysis, are guided from fundamental concepts to the state-of-the-art in research and practice.


@InCollection{titsias-mcmcgp11,
  title = 	 {Markov chain Monte Carlo algorithms for Gaussian processes},
  author = 	 {Michalis K. Titsias and Magnus Rattray and Neil D. Lawrence},
  booktitle = 	 {Bayesian Time Series Models},
  year = 	 {2011},
  editor = 	 {David Barber and A. Taylan Cemgil and Silvia Chiappa},
  month = 	 {00},
  publisher = 	 {Cambridge University Press},
  edit = 	 {https://github.com/lawrennd//publications/edit/gh-pages/_posts/2011-01-01-titsias-mcmcgp11.md},
  url =  	 {http://inverseprobability.com/publications/titsias-mcmcgp11.html},
  abstract = 	 {’What’s going to happen next?’ Time series data hold the answers, and Bayesian methods represent the cutting edge in learning what they have to say. This ambitious book is the first unified treatment of the emerging knowledge-base in Bayesian time series techniques. Exploiting the unifying framework of probabilistic graphical models, the book covers approximation schemes, both Monte Carlo and deterministic, and introduces switching, multi-object, non-parametric and agent-based models in a variety of application environments. It demonstrates that the basic framework supports the rapid creation of models tailored to specific applications and gives insight into the computational complexity of their implementation. The authors span traditional disciplines such as statistics and engineering and the more recently established areas of machine learning and pattern recognition. Readers with a basic understanding of applied probability, but no experience with time series analysis, are guided from fundamental concepts to the state-of-the-art in research and practice.},
  crossref =  {Barber:bayestime11},
  key = 	 {Titsias:mcmcgp11},
  chapter = 	 {14},
  OPTgroup = 	 {}
 

}
%T Markov chain Monte Carlo algorithms for Gaussian processes
%A Michalis K. Titsias and Magnus Rattray and Neil D. Lawrence
%B 
%C Bayesian Time Series Models
%D 
%E David Barber and A. Taylan Cemgil and Silvia Chiappa
%F titsias-mcmcgp11
%I Cambridge University Press	
%P --
%R 
%U http://inverseprobability.com/publications/titsias-mcmcgp11.html
%X ’What’s going to happen next?’ Time series data hold the answers, and Bayesian methods represent the cutting edge in learning what they have to say. This ambitious book is the first unified treatment of the emerging knowledge-base in Bayesian time series techniques. Exploiting the unifying framework of probabilistic graphical models, the book covers approximation schemes, both Monte Carlo and deterministic, and introduces switching, multi-object, non-parametric and agent-based models in a variety of application environments. It demonstrates that the basic framework supports the rapid creation of models tailored to specific applications and gives insight into the computational complexity of their implementation. The authors span traditional disciplines such as statistics and engineering and the more recently established areas of machine learning and pattern recognition. Readers with a basic understanding of applied probability, but no experience with time series analysis, are guided from fundamental concepts to the state-of-the-art in research and practice.
TY  - CPAPER
TI  - Markov chain Monte Carlo algorithms for Gaussian processes
AU  - Michalis K. Titsias
AU  - Magnus Rattray
AU  - Neil D. Lawrence
BT  - Bayesian Time Series Models
PY  - 2011/01/01
DA  - 2011/01/01
ED  - David Barber
ED  - A. Taylan Cemgil
ED  - Silvia Chiappa	
ID  - titsias-mcmcgp11
PB  - Cambridge University Press	
SP  - 
EP  - 
UR  - http://inverseprobability.com/publications/titsias-mcmcgp11.html
AB  - ’What’s going to happen next?’ Time series data hold the answers, and Bayesian methods represent the cutting edge in learning what they have to say. This ambitious book is the first unified treatment of the emerging knowledge-base in Bayesian time series techniques. Exploiting the unifying framework of probabilistic graphical models, the book covers approximation schemes, both Monte Carlo and deterministic, and introduces switching, multi-object, non-parametric and agent-based models in a variety of application environments. It demonstrates that the basic framework supports the rapid creation of models tailored to specific applications and gives insight into the computational complexity of their implementation. The authors span traditional disciplines such as statistics and engineering and the more recently established areas of machine learning and pattern recognition. Readers with a basic understanding of applied probability, but no experience with time series analysis, are guided from fundamental concepts to the state-of-the-art in research and practice.
ER  -

Titsias, M.K., Rattray, M. & Lawrence, N.D.. (2011). Markov chain Monte Carlo algorithms for Gaussian processes. Bayesian Time Series Models :-