.png){kind=icon}
.png){kind=icon}
Return
Explainable Gaussian processes: a loss landscape perspective
.png){kind=icon}
OA
AI
DOI：10.1088/2632-2153/ad62ad.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Prior beliefs about the latent function to shape inductive biases can be incorporated into a Gaussian process (GP) via the kernel. However, beyond kernel choices, the decision-making process of GP models remains poorly understood. In this work, we contribute an analysis of the loss landscape for GP models using methods from chemical physics. We demonstrate nu-continuity for Mat & eacute;rn kernels and outline aspects of catastrophe theory at critical points in the loss landscape. By directly including nu in the hyperparameter optimisation for Mat & eacute;rn kernels, we find that typical values of nu can be far from optimal in terms of performance. We also provide an a priori method for evaluating the effect of GP ensembles and discuss various voting approaches based on physical properties of the loss landscape. The utility of these approaches is demonstrated for various synthetic and real datasets. Our findings provide insight into hyperparameter optimisation for GPs and offer practical guidance for improving their performance and interpretability in a range of applications.
Keywords:
loss landscapes
Gaussian processes
machine learning
physics-inspired
Journal
M
IF:
4.6
Papers:
1.1K
Citations:
3.4K