Practical and Rigorous Uncertainty Bounds for Gaussian Process Regression

by   Christian Fiedler, et al.

Gaussian Process Regression is a popular nonparametric regression method based on Bayesian principles that provides uncertainty estimates for its predictions. However, these estimates are of a Bayesian nature, whereas for some important applications, like learning-based control with safety guarantees, frequentist uncertainty bounds are required. Although such rigorous bounds are available for Gaussian Processes, they are too conservative to be useful in applications. This often leads practitioners to replacing these bounds by heuristics, thus breaking all theoretical guarantees. To address this problem, we introduce new uncertainty bounds that are rigorous, yet practically useful at the same time. In particular, the bounds can be explicitly evaluated and are much less conservative than state of the art results. Furthermore, we show that certain model misspecifications lead to only graceful degradation. We demonstrate these advantages and the usefulness of our results for learning-based control with numerical examples.



There are no comments yet.


page 7


Learning-enhanced robust controller synthesis with rigorous statistical and control-theoretic guarantees

The combination of machine learning with control offers many opportuniti...

Gaussian Process Uniform Error Bounds with Unknown Hyperparameters for Safety-Critical Applications

Gaussian processes have become a promising tool for various safety-criti...

Symplectic Gaussian Process Dynamics

Dynamics model learning is challenging and at the same time an active fi...

Heteroscedastic Gaussian Process Regression on the Alkenone over Sea Surface Temperatures

To restore the historical sea surface temperatures (SSTs) better, it is ...

Robust Regression for Safe Exploration in Control

We study the problem of safe learning and exploration in sequential cont...

Finite-Data Performance Guarantees for the Output-Feedback Control of an Unknown System

As the systems we control become more complex, first-principle modeling ...

The Value of Data in Learning-Based Control for Training Subset Selection

Despite the existence of formal guarantees for learning-based control ap...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.