ICML 2019oral218 citations

Rates of Convergence for Sparse Variational Gaussian Process Regression

David Burt, Carl Edward Rasmussen, Mark Van Der Wilk

Abstract

Excellent variational approximations to Gaussian process posteriors have been developed which avoid the $\mathcal{O}\left(N^3\right)$ scaling with dataset size $N$. They reduce the computational cost to $\mathcal{O}\left(NM^2\right)$, with $M\ll N$ the number of

BibTeX
@InProceedings{pmlr-v97-burt19a,
  title = 	 {Rates of Convergence for Sparse Variational {G}aussian Process Regression},
  author =       {Burt, David and Rasmussen, Carl Edward and Van Der Wilk, Mark},
  booktitle = 	 {Proceedings of the 36th International Conference on Machine Learning},
  pages = 	 {862--871},
  year = 	 {2019},
  editor = 	 {Chaudhuri, Kamalika and Salakhutdinov, Ruslan},
  volume = 	 {97},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {09--15 Jun},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v97/burt19a/burt19a.pdf},
  url = 	 {https://proceedings.mlr.press/v97/burt19a.html},
  abstract = 	 {Excellent variational approximations to Gaussian process posteriors have been developed which avoid the $\mathcal{O}\left(N^3\right)$ scaling with dataset size $N$. They reduce the computational cost to $\mathcal{O}\left(NM^2\right)$, with $M\ll N$ the number of