An Enhanced Probability of Improvement Utility Function for Locating Pareto Optimal Solutions

摘要

This paper describes a novel utility function for choosing design vectors to evaluate in multi-objective optimization problems which are statistically most probable to be Paretooptimal, given the points already evaluated. The method is tunable to the number of existing Pareto-optimal solutions that an unevaluated design vector is sought to dominate, is naturally parallelized, and removes any need for combining the multiple objectives into a single objective with a scalarizing function.