AI RESEARCH
Amortized Multi-Objective Optimization Across Tasks with Generative Solution Modeling
arXiv CS.LG
•
ArXi:2511.09598v5 Announce Type: replace Many real-world applications require solving families of expensive multi-objective optimization problems~(EMOPs) under varying operational conditions. This can be formulated as parametric expensive multi-objective optimization problems (P-EMOPs) where each task parameter defines a distinct optimization instance. Current multi-objective Bayesian optimization methods have been widely used for finding finite sets of Pareto optimal solutions for each task.