Gaussian Processes for Big Data

James Hensman, Nicolo Fusi, Neil Lawrence
Proceedings of the 29th Conference on Uncertainty in Artificial Intelligence, PMLR R11:432-440, 2013.

Abstract

We introduce stochastic variational inference for Gaussian process models. This enables the application of Gaussian process (GP) models to data sets containing millions of data points. We show how GPs can be vari- ationally decomposed to depend on a set of globally relevant inducing variables which factorize the model in the necessary manner to perform variational inference. Our ap- proach is readily extended to models with non-Gaussian likelihoods and latent variable models based around Gaussian processes. We demonstrate the approach on a simple toy problem and two real world data sets.

Cite this Paper

BibTeX
@InProceedings{pmlr-vR11-hensman13a, title = {{G}aussian Processes for Big Data}, author = {Hensman, James and Fusi, Nicolo and Lawrence, Neil}, booktitle = {Proceedings of the 29th Conference on Uncertainty in Artificial Intelligence}, pages = {432--440}, year = {2013}, editor = {Nicholson, Ann and Smyth, Padhraic}, volume = {R11}, series = {Proceedings of Machine Learning Research}, month = {12--14 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/r11/main/assets/hensman13a/hensman13a.pdf}, url = {https://proceedings.mlr.press/r11/hensman13a.html}, abstract = {We introduce stochastic variational inference for Gaussian process models. This enables the application of Gaussian process (GP) models to data sets containing millions of data points. We show how GPs can be vari- ationally decomposed to depend on a set of globally relevant inducing variables which factorize the model in the necessary manner to perform variational inference. Our ap- proach is readily extended to models with non-Gaussian likelihoods and latent variable models based around Gaussian processes. We demonstrate the approach on a simple toy problem and two real world data sets.}, note = {Reissued by PMLR on 04 October 2026.} }
Endnote
%0 Conference Paper %T Gaussian Processes for Big Data %A James Hensman %A Nicolo Fusi %A Neil Lawrence %B Proceedings of the 29th Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2013 %E Ann Nicholson %E Padhraic Smyth %F pmlr-vR11-hensman13a %I PMLR %P 432--440 %U https://proceedings.mlr.press/r11/hensman13a.html %V R11 %X We introduce stochastic variational inference for Gaussian process models. This enables the application of Gaussian process (GP) models to data sets containing millions of data points. We show how GPs can be vari- ationally decomposed to depend on a set of globally relevant inducing variables which factorize the model in the necessary manner to perform variational inference. Our ap- proach is readily extended to models with non-Gaussian likelihoods and latent variable models based around Gaussian processes. We demonstrate the approach on a simple toy problem and two real world data sets. %Z Reissued by PMLR on 04 October 2026.
APA
Hensman, J., Fusi, N. & Lawrence, N.. (2013). Gaussian Processes for Big Data. Proceedings of the 29th Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research R11:432-440 Available from https://proceedings.mlr.press/r11/hensman13a.html. Reissued by PMLR on 04 October 2026.

Related Material