JAREX: An Acquisition Function for Multi-Objective Algorithmic Process Characterization

Process characterization defines how variations in process parameters affect the ability to meet product quality specifications. Current factorial design-of-experiments approaches are inefficient for resolving multivariate pass/fail boundaries in higher-dimensional spaces, and adaptive methods for multi-objective process characterization remain lacking. We introduce JAREX (Joint Acceptable Region EXploration), a Bayesian active-learning acquisition function that adaptively selects experiments to recover the joint pass region defined by simultaneous satisfaction of threshold criteria across multiple objectives. JAREX combines an optimistic joint-feasibility mask with a multi-objective extension of randomized straddle, focusing sampling on the joint edge of failure. On a simulated kinetic model, JAREX provides more accurate and sample-efficient recovery of the joint pass region than factorial DOE, space-filling designs, and greedy objective-wise strategies. For batched experimentation, it reduces the number of iterative experiments by more than half while preserving high accuracy for boundary identification.