This book presents the state of the art in designing high-performance algorithms that combine simulation and optimization in order to solve complex optimization problems in science and industry, problems that involve time-consuming simulations and expensive multi-objective function evaluations. As traditional optimization approaches are not applicable per se, combinations of computational intelligence, machine learning, and high-performance computing methods are popular solutions. But finding a suitable method is a challenging task, because numerous approaches have been proposed in this highly dynamic field of research. That's where this book comes in: It covers both theory and practice, drawing on the real-world insights gained by the contributing authors, all of whom are leading researchers. Given its scope, if offers a comprehensive reference guide for researchers, practitioners, and advanced-level students interested in using computational intelligence and machine learning to solve expensive optimization problems.
Infill Criteria for Multiobjective Bayesian Optimization.- Many-Objective Optimization with Limited Computing Budget.- Multi-Objective Bayesian Optimization for Engineering Simulation.- Automatic Configuration of Multi-Objective Optimizers and Multi-Objective Configuration.- Optimization and Visualization in Many-Objective Space Trajectory Design.- Simulation Optimization through Regression or Kriging Metamodels.- Towards Better Integration of Surrogate Models and Optimizers.- Surrogate-Assisted Evolutionary Optimization of Large Problems.- Overview and Comparison of Gaussian Process-Based Surrogate Models for Mixed Continuous and Discrete Variables: Application on Aerospace Design Problems.- Open Issues in Surrogate-Assisted Optimization.- A Parallel Island Model for Hypervolume-Based Many-Objective Optimization.- Many-Core Branch-and-Bound for GPU Accelerators and MIC Coprocessors.
