Wynne, G;
Briol, FX;
Girolami, M;
(2021)
Convergence guarantees for gaussian process means with misspecified likelihoods and smoothness.
Journal of Machine Learning Research
, 22
, Article 123.
Preview |
Text
20-662.pdf - Published Version Download (467kB) | Preview |
Abstract
Gaussian processes are ubiquitous in machine learning, statistics, and applied mathematics. They provide a exible modelling framework for approximating functions, whilst simultaneously quantifying uncertainty. However, this is only true when the model is well-specifoed, which is often not the case in practice. In this paper, we study the properties of Gaussian process means when the smoothness of the model and the likelihood function are misspecified. In this setting, an important theoretical question of practical relevance is how accurate the Gaussian process approximations will be given the chosen model and the extent of the misspecification. The answer to this problem is particularly useful since it can inform our choice of model and experimental design. In particular, we describe how the experimental design and choice of kernel and kernel hyperparameters can be adapted to alleviate model misspecification.
Type: | Article |
---|---|
Title: | Convergence guarantees for gaussian process means with misspecified likelihoods and smoothness |
Open access status: | An open access version is available from UCL Discovery |
Publisher version: | https://jmlr.org/papers/v22/20-662.html |
Language: | English |
Additional information: | © 2021 George Wynne, Fran¸cois-Xavier Briol, Mark Girolami. License: CC-BY 4.0, see https://creativecommons.org/licenses/by/4.0/. Attribution requirements are provided at http://jmlr.org/papers/v22/20-662.html |
Keywords: | Gaussian Processes, Kriging, Nonparametric Regression, Reproducing Kernel Hilbert Space, Sampling Inequality |
UCL classification: | UCL UCL > Provost and Vice Provost Offices UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences > Dept of Statistical Science |
URI: | https://discovery.ucl.ac.uk/id/eprint/10130494 |
Archive Staff Only
View Item |