Surrogates : Gaussian Process Modeling, Design, and Optimization for the Applied Sciences (Hardcover)

Preface 1 Historical Perspective 1.1 Response surface methodology 1.2 Computer experiments 1.3 A road map 1.4 Homework exercises 2 Four Motivating Datasets 312.1 Rocket booster dynamics2.2 Radiative shock hydrodynamics2.3 Predicting satellite drag2.4 Groundwater remediation 2.5 Data out there 2.6 Homework exercises 3 Steepest Ascent and Ridge Analysis3.1 Path of steepest ascent 3.2 Second-order response surfaces3.3 Homework exercises 4 Space-filling Design 4.1 Latin hypercube sample4.2 Maximin designs 4.3 Libraries and hybrids 4.4 Homework exercises 5 Gaussian process regression 5.1 Gaussian process prior 5.2 GP hyperparameters5.3 Some interpretation and perspective 5.4 Challenges & remedies 5.5 Homework exercises 6 Model-Based Design for GPs 6.1 Model-based design 6.2 Sequential design/active learning 6.3 Fast GP updates 6.4 Homework exercises 7 Optimization7.1 Surrogate-assisted optimization7.2 Expected improvement7.3 Optimization under constraints7.4 Homework exercises 8 Calibration and Sensitivity 8.1 Calibration8.2 Sensitivity analysis 8.3 Homework exercises 9 GP Fidelity and Scale 9.1 Compactly supported kernels 9.2 Partition models and regression trees 9.3 Local approximate GPs 9.4 Homework exercises 10 Heteroskedasticity 10.1 Replication and stochastic kriging 10.2 Coupled mean and variance GPs10.3 Sequential design 10.4 Homework exercises AppendixA Numerical Linear Algebra for Fast GPs 501A.1 Intel MKL and OSX Accelerate A.2 Stochastic approximation B An Experiment Game B.1 A shiny update to an old game B.2 Benchmarking play in real-time Bibliography Index