Warped Gaussian Processes
Abstract
We generalise the Gaussian process (GP) framework for regression by learning a nonlinear transformation of the GP outputs. This allows for non-Gaussian processes and non-Gaussian noise. The learning algo- rithm chooses a nonlinear transformation such that transformed data is well-modelled by a GP. This can be seen as including a preprocessing transformation as an integral part of the probabilistic modelling problem, rather than as an ad-hoc step. We demonstrate on several real regression problems that learning the transformation can lead to significantly better performance than using a regular GP, or a GP with a fixed transformation.
Cite
Text
Snelson et al. "Warped Gaussian Processes." Neural Information Processing Systems, 2003.Markdown
[Snelson et al. "Warped Gaussian Processes." Neural Information Processing Systems, 2003.](https://mlanthology.org/neurips/2003/snelson2003neurips-warped/)BibTeX
@inproceedings{snelson2003neurips-warped,
title = {{Warped Gaussian Processes}},
author = {Snelson, Edward and Ghahramani, Zoubin and Rasmussen, Carl E.},
booktitle = {Neural Information Processing Systems},
year = {2003},
pages = {337-344},
url = {https://mlanthology.org/neurips/2003/snelson2003neurips-warped/}
}