User: Guest  Login
Title:

Solving Bayesian Inverse Problems With Expensive Likelihoods Using Constrained Gaussian Processes and Active Learning

Document type:
Zeitschriftenaufsatz
Author(s):
Maximilian Dinkel, Carolin M. Geitner, Gil Robalo Rei, Jonas Nitzler, Wolfgang A. Wall
Abstract:
Solving inverse problems using Bayesian methods can become prohibitively expensive when likelihood evaluations involve complex and large scale numerical models. A common approach to circumvent this issue is to approximate the forward model or the likelihood function with a surrogate model. But also there, due to limited computational resources, only a few training points are available in many practically relevant cases. Thus, it can be advantageous to model the additional uncertainties of the su...     »
Keywords:
Bayesian inverse problem, Gaussian process, active learning
Journal title:
Inverse Problems
Year:
2024
Reviewed:
ja
Language:
en
Fulltext / DOI:
doi:10.1088/1361-6420/ad5eb4
Status:
Verlagsversion / published
 BibTeX