Our model can also serve as a plug-and-play replacement for shallow manifold GPs in geometry-aware Bayesian optimisation. This can be especially useful for complex target functions, as we demonstrate experimentally. 6/n
Comments
Log in with your Bluesky account to leave a comment
We test our model on the ERA5 dataset – interpolating wind on the globe from a set of points on a satellite trajectory. Our model outperforms baselines, yielding accurate and interpretable uncertainty estimates. An example predictive mean and variance is shown below. 7/n
All this is with little to no fine-tuning! Simply initialising hidden layers with a small variance allows our model to use additional layers just when necessary, preventing overfitting in our experiments.
Comments
See our paper here: https://arxiv.org/abs/2411.00161. 9/n