Active Discrimination Learning for Gaussian Process Models

by   Elham Yousefi, et al.

The paper covers the design and analysis of experiments to discriminate between two Gaussian process models, such as those widely used in computer experiments, kriging, sensor location and machine learning. Two frameworks are considered. First, we study sequential constructions, where successive design (observation) points are selected, either as additional points to an existing design or from the beginning of observation. The selection relies on the maximisation of the difference between the symmetric Kullback Leibler divergences for the two models, which depends on the observations, or on the mean squared error of both models, which does not. Then, we consider static criteria, such as the familiar log-likelihood ratios and the Fréchet distance between the covariance functions of the two models. Other distance-based criteria, simpler to compute than previous ones, are also introduced, for which, considering the framework of approximate design, a necessary condition for the optimality of a design measure is provided. The paper includes a study of the mathematical links between different criteria and numerical illustrations are provided.


page 1

page 2

page 3

page 4


Interpolation error of misspecified Gaussian process regression

An interpolation error is an integral of the squared error of a regressi...

Gaussian process interpolation: the choice of the family of models is more important than that of the selection criterion

This article revisits the fundamental problem of parameter selection for...

Parallel Gaussian process surrogate method to accelerate likelihood-free inference

We consider Bayesian inference when only a limited number of noisy log-l...

Additive Covariance Kernels for High-Dimensional Gaussian Process Modeling

Gaussian process models -also called Kriging models- are often used as m...

GPdoemd: a Python package for design of experiments for model discrimination

Model discrimination identifies a mathematical model that usefully expla...

Universal Convergence of Kriging

Kriging based on Gaussian random fields is widely used in reconstructing...

Please sign up or login with your details

Forgot password? Click here to reset