Finite-Dimensional Approximation of Gaussian Processes

Abstract

Gaussian process (GP) prediction suffers from O(n3) scaling with the data set size n. By using a finite-dimensional basis to approximate the GP predictor, the computational complexity can be reduced. We de(cid:173) rive optimal finite-dimensional predictors under a number of assump(cid:173) tions, and show the superiority of these predictors over the Projected Bayes Regression method (which is asymptotically optimal). We also show how to calculate the minimal model size for a given n. The calculations are backed up by numerical experiments.

Cite

Text

Ferrari-Trecate et al. "Finite-Dimensional Approximation of Gaussian Processes." Neural Information Processing Systems, 1998.

Markdown

[Ferrari-Trecate et al. "Finite-Dimensional Approximation of Gaussian Processes." Neural Information Processing Systems, 1998.](https://mlanthology.org/neurips/1998/ferraritrecate1998neurips-finitedimensional/)

BibTeX

@inproceedings{ferraritrecate1998neurips-finitedimensional,
  title     = {{Finite-Dimensional Approximation of Gaussian Processes}},
  author    = {Ferrari-Trecate, Giancarlo and Williams, Christopher K. I. and Opper, Manfred},
  booktitle = {Neural Information Processing Systems},
  year      = {1998},
  pages     = {218-224},
  url       = {https://mlanthology.org/neurips/1998/ferraritrecate1998neurips-finitedimensional/}
}