YG84SWm7gn@OpenReview

Total: 1

#1 Robust and Conjugate Spatio-Temporal Gaussian Processes [PDF] [Copy] [Kimi] [REL]

Authors: William Laplante, Matias Altamirano, Andrew Duncan, Jeremias Knoblauch, Francois-Xavier Briol

State-space formulations allow for Gaussian process (GP) regression with linear-in-time computational cost in spatio-temporal settings, but performance typically suffers in the presence of outliers. In this paper, we adapt and specialise the *robust and conjugate GP (RCGP)* framework of Altamirano et al. (2024) to the spatio-temporal setting. In doing so, we obtain an outlier-robust spatio-temporal GP with a computational cost comparable to classical spatio-temporal GPs. We also overcome the three main drawbacks of RCGPs: their unreliable performance when the prior mean is chosen poorly, their lack of reliable uncertainty quantification, and the need to carefully select a hyperparameter by hand. We study our method extensively in finance and weather forecasting applications, demonstrating that it provides a reliable approach to spatio-temporal modelling in the presence of outliers.

Subject: ICML.2025 - Poster