The Cost of Numerical Integration in Statistical Decision-theoretic Methods for Robust Design Optimization

摘要: The Bayes principle from statistical decision theory provides a conceptual framework for quantifying uncertainties that arise in robust design optimization. difficulty with exploiting this framework is computational, as it leads to objective and constraint functions that must be evaluated by numerical integration. Using prototypical optimization problem, study explores the computational cost of multidimensional integration (computing expectation) its interplay with optimization algorithms. It concludes straightforward application standard off-the-shelf software prohibitively expensive, necessitating adaptive strategies use surrogates.