Adaptive Gradient Enhanced Gaussian Process Surrogates for Inverse Problems
accepted for publication
- Generating simulated training data needed for constructing sufficiently accurate surrogate models to be used for efficient optimization or parameter identification can incur a huge computational effort in the offline phase. We consider a fully adaptive greedy approach to the computational design of experiments problem using gradient-enhanced Gaussian process regression as surrogates. Designs are incrementally defined by solving an optimization problem for accuracy given a certain computational budget. We address not only the choice of evaluation points but also of required simulation accuracy, both of values and gradients of the forward model. Numerical results show a significant reduction of the computational effort compared to just position-adaptive and static designs as well as a clear benefit of including gradient information into the surrogate training.
Author: | Phillip Semler, Martin WeiserORCiD |
---|---|
Document Type: | In Proceedings |
Parent Title (English): | Proceedings of the MATH+ Thematic Einstein Semester on Mathematical Optimization for Machine Learning |
Year of first publication: | 2024 |
ArXiv Id: | http://arxiv.org/abs/2404.01864 |