Scaling Multidimensional Gaussian Processes using Projected Additive Approximations

Elad Gilboa, Yunus Saatçi, John Cunningham, Elad Gilboa
Proceedings of the 30th International Conference on Machine Learning, PMLR 28(1):454-461, 2013.

Abstract

Exact Gaussian Process (GP) regression has O(N^3) runtime for data size N, making it intractable for large N. Advances in GP scaling have not been extended to the multidimensional input setting, despite the preponderance of multidimensional applications. This paper introduces and tests a novel method of projected additive approximation to multidimensional GPs. We thoroughly illustrate the power of this method on several datasets, achieving close performance to the naive Full GP at orders of magnitude less cost.

Cite this Paper

BibTeX
@InProceedings{pmlr-v28-gilboa13, title = {Scaling Multidimensional {G}aussian Processes using Projected Additive Approximations}, author = {Gilboa, Elad and Saatçi, Yunus and Cunningham, John and Gilboa, Elad}, booktitle = {Proceedings of the 30th International Conference on Machine Learning}, pages = {454--461}, year = {2013}, editor = {Dasgupta, Sanjoy and McAllester, David}, volume = {28}, number = {1}, series = {Proceedings of Machine Learning Research}, address = {Atlanta, Georgia, USA}, month = {17--19 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v28/gilboa13.pdf}, url = {https://proceedings.mlr.press/v28/gilboa13.html}, abstract = {Exact Gaussian Process (GP) regression has O(N^3) runtime for data size N, making it intractable for large N. Advances in GP scaling have not been extended to the multidimensional input setting, despite the preponderance of multidimensional applications. This paper introduces and tests a novel method of projected additive approximation to multidimensional GPs. We thoroughly illustrate the power of this method on several datasets, achieving close performance to the naive Full GP at orders of magnitude less cost.} }
Endnote
%0 Conference Paper %T Scaling Multidimensional Gaussian Processes using Projected Additive Approximations %A Elad GilboaYunus Saatçi %A John Cunningham %A Elad Gilboa %B Proceedings of the 30th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2013 %E Sanjoy Dasgupta %E David McAllester %F pmlr-v28-gilboa13 %I PMLR %P 454--461 %U https://proceedings.mlr.press/v28/gilboa13.html %V 28 %N 1 %X Exact Gaussian Process (GP) regression has O(N^3) runtime for data size N, making it intractable for large N. Advances in GP scaling have not been extended to the multidimensional input setting, despite the preponderance of multidimensional applications. This paper introduces and tests a novel method of projected additive approximation to multidimensional GPs. We thoroughly illustrate the power of this method on several datasets, achieving close performance to the naive Full GP at orders of magnitude less cost.
RIS
TY - CPAPER TI - Scaling Multidimensional Gaussian Processes using Projected Additive Approximations AU - Elad GilboaYunus Saatçi AU - John Cunningham AU - Elad Gilboa BT - Proceedings of the 30th International Conference on Machine Learning DA - 2013/02/13 ED - Sanjoy Dasgupta ED - David McAllester ID - pmlr-v28-gilboa13 PB - PMLR DP - Proceedings of Machine Learning Research VL - 28 IS - 1 SP - 454 EP - 461 L1 - http://proceedings.mlr.press/v28/gilboa13.pdf UR - https://proceedings.mlr.press/v28/gilboa13.html AB - Exact Gaussian Process (GP) regression has O(N^3) runtime for data size N, making it intractable for large N. Advances in GP scaling have not been extended to the multidimensional input setting, despite the preponderance of multidimensional applications. This paper introduces and tests a novel method of projected additive approximation to multidimensional GPs. We thoroughly illustrate the power of this method on several datasets, achieving close performance to the naive Full GP at orders of magnitude less cost. ER -
APA
Gilboa, E.Saatçi, Y., Cunningham, J. & Gilboa, E.. (2013). Scaling Multidimensional Gaussian Processes using Projected Additive Approximations. Proceedings of the 30th International Conference on Machine Learning, in Proceedings of Machine Learning Research 28(1):454-461 Available from https://proceedings.mlr.press/v28/gilboa13.html.

Related Material