A parametric multi-objective Bayesian optimizer amortizes optimization across continuous task spaces by alternating generative solution sampling and acquisition-driven search to enable direct prediction for unseen problems without re-evaluations.
Differentiable expected hypervolume improvement for parallel multi-objective bayesian optimization.Advances in Neural Information Processing Systems, 33:9851– 9864
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Amortized Multi-Objective Optimization Across Tasks with Generative Solution Modeling
A parametric multi-objective Bayesian optimizer amortizes optimization across continuous task spaces by alternating generative solution sampling and acquisition-driven search to enable direct prediction for unseen problems without re-evaluations.