Elliptical slice sampling

Iain Murray, Ryan Adams, David MacKay
; Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, JMLR Workshop and Conference Proceedings 9:541-548, 2010.

Abstract

Many probabilistic models introduce strong dependencies between variables using a latent multivariate Gaussian distribution or a Gaussian process. We present a new Markov chain Monte Carlo algorithm for performing inference in models with multivariate Gaussian priors. Its key properties are: 1) it has simple, generic code applicable to many models, 2) it has no free parameters, 3) it works well for a variety of Gaussian process based models. These properties make our method ideal for use while model building, removing the need to spend time deriving and tuning updates for more complex algorithms.

Cite this Paper


BibTeX
@InProceedings{pmlr-v9-murray10a, title = {Elliptical slice sampling}, author = {Iain Murray and Ryan Adams and David MacKay}, booktitle = {Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics}, pages = {541--548}, year = {2010}, editor = {Yee Whye Teh and Mike Titterington}, volume = {9}, series = {Proceedings of Machine Learning Research}, address = {Chia Laguna Resort, Sardinia, Italy}, month = {13--15 May}, publisher = {JMLR Workshop and Conference Proceedings}, pdf = {http://proceedings.mlr.press/v9/murray10a/murray10a.pdf}, url = {http://proceedings.mlr.press/v9/murray10a.html}, abstract = {Many probabilistic models introduce strong dependencies between variables using a latent multivariate Gaussian distribution or a Gaussian process. We present a new Markov chain Monte Carlo algorithm for performing inference in models with multivariate Gaussian priors. Its key properties are: 1) it has simple, generic code applicable to many models, 2) it has no free parameters, 3) it works well for a variety of Gaussian process based models. These properties make our method ideal for use while model building, removing the need to spend time deriving and tuning updates for more complex algorithms.} }
Endnote
%0 Conference Paper %T Elliptical slice sampling %A Iain Murray %A Ryan Adams %A David MacKay %B Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2010 %E Yee Whye Teh %E Mike Titterington %F pmlr-v9-murray10a %I PMLR %J Proceedings of Machine Learning Research %P 541--548 %U http://proceedings.mlr.press %V 9 %W PMLR %X Many probabilistic models introduce strong dependencies between variables using a latent multivariate Gaussian distribution or a Gaussian process. We present a new Markov chain Monte Carlo algorithm for performing inference in models with multivariate Gaussian priors. Its key properties are: 1) it has simple, generic code applicable to many models, 2) it has no free parameters, 3) it works well for a variety of Gaussian process based models. These properties make our method ideal for use while model building, removing the need to spend time deriving and tuning updates for more complex algorithms.
RIS
TY - CPAPER TI - Elliptical slice sampling AU - Iain Murray AU - Ryan Adams AU - David MacKay BT - Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics PY - 2010/03/31 DA - 2010/03/31 ED - Yee Whye Teh ED - Mike Titterington ID - pmlr-v9-murray10a PB - PMLR SP - 541 DP - PMLR EP - 548 L1 - http://proceedings.mlr.press/v9/murray10a/murray10a.pdf UR - http://proceedings.mlr.press/v9/murray10a.html AB - Many probabilistic models introduce strong dependencies between variables using a latent multivariate Gaussian distribution or a Gaussian process. We present a new Markov chain Monte Carlo algorithm for performing inference in models with multivariate Gaussian priors. Its key properties are: 1) it has simple, generic code applicable to many models, 2) it has no free parameters, 3) it works well for a variety of Gaussian process based models. These properties make our method ideal for use while model building, removing the need to spend time deriving and tuning updates for more complex algorithms. ER -
APA
Murray, I., Adams, R. & MacKay, D.. (2010). Elliptical slice sampling. Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, in PMLR 9:541-548

Related Material