Sparse Gaussian Processes for Bayesian Optimization

Mitchell McIntire, Daniel Ratner SLAC National Accelerator Laboratory, Stefano Ermon
Proceedings of the 32nd Conference on Uncertainty in Artificial Intelligence, PMLR R14:762-771, 2016.

Abstract

Bayesian optimization schemes often rely on Gaussian processes (GP). GP models are very flexible, but are known to scale poorly with the number of training points. While several efficient sparse GP models are known, they have limitations when applied in optimization settings.We propose a novel Bayesian optimization framework that uses sparse online Gaussian processes. We introduce a new updating scheme for the online GP that accounts for our preference during optimization for regions with better performance. We apply this method to optimize the performance of a free-electron laser, and demonstrate empirically that the weighted updating scheme leads to substantial improvements to performance in optimization.

Cite this Paper

BibTeX
@InProceedings{pmlr-vR14-mcintire16a, title = {Sparse {G}aussian Processes for {B}ayesian Optimization}, author = {McIntire, Mitchell and Laboratory, Daniel Ratner SLAC National Accelerator and Ermon, Stefano}, booktitle = {Proceedings of the 32nd Conference on Uncertainty in Artificial Intelligence}, pages = {762--771}, year = {2016}, editor = {Ihler, Alexander and Janzing, Dominik}, volume = {R14}, series = {Proceedings of Machine Learning Research}, month = {25--29 Jun}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/r14/main/assets/mcintire16a/mcintire16a.pdf}, url = {https://proceedings.mlr.press/r14/mcintire16a.html}, abstract = {Bayesian optimization schemes often rely on Gaussian processes (GP). GP models are very flexible, but are known to scale poorly with the number of training points. While several efficient sparse GP models are known, they have limitations when applied in optimization settings.We propose a novel Bayesian optimization framework that uses sparse online Gaussian processes. We introduce a new updating scheme for the online GP that accounts for our preference during optimization for regions with better performance. We apply this method to optimize the performance of a free-electron laser, and demonstrate empirically that the weighted updating scheme leads to substantial improvements to performance in optimization.}, note = {Reissued by PMLR on 04 October 2026.} }
Endnote
%0 Conference Paper %T Sparse Gaussian Processes for Bayesian Optimization %A Mitchell McIntire %A Daniel Ratner SLAC National Accelerator Laboratory %A Stefano Ermon %B Proceedings of the 32nd Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2016 %E Alexander Ihler %E Dominik Janzing %F pmlr-vR14-mcintire16a %I PMLR %P 762--771 %U https://proceedings.mlr.press/r14/mcintire16a.html %V R14 %X Bayesian optimization schemes often rely on Gaussian processes (GP). GP models are very flexible, but are known to scale poorly with the number of training points. While several efficient sparse GP models are known, they have limitations when applied in optimization settings.We propose a novel Bayesian optimization framework that uses sparse online Gaussian processes. We introduce a new updating scheme for the online GP that accounts for our preference during optimization for regions with better performance. We apply this method to optimize the performance of a free-electron laser, and demonstrate empirically that the weighted updating scheme leads to substantial improvements to performance in optimization. %Z Reissued by PMLR on 04 October 2026.
APA
McIntire, M., Laboratory, D.R.S.N.A. & Ermon, S.. (2016). Sparse Gaussian Processes for Bayesian Optimization. Proceedings of the 32nd Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research R14:762-771 Available from https://proceedings.mlr.press/r14/mcintire16a.html. Reissued by PMLR on 04 October 2026.

Related Material