Refine
Year of publication
Document Type
- Article (63)
- In Proceedings (20)
- In Collection (9)
- Book (4)
- Book chapter (3)
- Report (1)
- Software (1)
Has Fulltext
- no (101) (remove)
Is part of the Bibliography
- no (101)
Keywords
Institute
- Numerical Mathematics (84)
- Computational Medicine (60)
- Modeling and Simulation of Complex Processes (29)
- Visual Data Analysis (8)
- Visual and Data-centric Computing (8)
- Mathematics for Life and Materials Science (6)
- Therapy Planning (6)
- Network Optimization (4)
- Computational Nano Optics (2)
- Distributed Algorithms and Supercomputing (2)
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.