MOBO-CAPS: Multi-Objective Bayesian Optimization with Cardinality-Aware Pareto Selection
Organizations: University of Warwick, Coventry, CV4 7AL, United Kingdom · Databricks, San Francisco, CA 94105, USA
Abstract
Multi-objective Bayesian optimization (MOBO) traditionally aims to approximate the entire Pareto front, but, due to resource constraints, real-world deployment is often limited to testing a small, representative subset of solutions. Hence current methods first approximate the full front before selecting solutions, potentially wasting costly evaluations. We formalize this problem as Multi-objective Bayesian Optimization with Cardinality-aware Pareto Selection (MOBO-CAPS), where the goal is to identify a set of exactly M solutions with high hypervolume. We propose two practical cardinality-aware acquisition strategies: REHVI, a replacement-aware approximation to expected hypervolume improvement, and CHO-UCB, which constructs an optimistic M-point set by optimizing a collective UCB-based hypervolume objective. We prove a sublinear simple regret bound for the batched version of CHO-UCB, and empirically show that cardinality-aware acquisition design improves over standard MOBO followed by post-hoc subset selection across nine benchmarks.
Figures & tables
| MOBO-CAPS Methods | Baselines | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| Setting | REHVI | CHO-UCB | EHVI | SMS-EGO | HV-KG | ParEGO* | ParEGO | JES | Sobol |
| Overall | |||||||||
Appendix figures & tables18 assets
Supplementary material from the paper’s appendix.
Appendix
| Setting | Metric | Cardinality | Objective Function Property |
|---|---|---|---|
| Traditional MOBO | Hypervolume | No limit | Black-box |
| MOBO-CAPS | Hypervolume | Black-box | |
| BOPE [ Lin et al., 2022 ] | Utility Function | 1 | Black-box |
| Knee Finding [ Heidari et al., 2022 ] | Hypervolume | 1 | Black-box |
| Coverage BO [ Maus et al., 2025 ] | Coverage Score | Black-box | |
| HIGA-MO [ Wang et al., 2017 ] | Hypervolume | Accessible Gradient |
| Sobol | ParEGO | ParEGO* | JES | HV-KG | SMS-EGO | EHVI | CHO-UCB | REHVI | |
|---|---|---|---|---|---|---|---|---|---|
| BraninCurrin ( ) | |||||||||
| BraninCurrin ( ) | |||||||||
| BraninCurrin ( ) | |||||||||
| BraninCurrin ( ) | |||||||||
| BraninCurrin ( ) | |||||||||
| DTLZ1 ( ) |
Bayesian Optimization
Bayesian optimization uses probabilistic models and sequential experiments to find strong solutions when evaluating a black-box objective is costly.
See all 271 papers