Abstract
Bayesian optimization often involves multiple objectives, constraints, and fidelity levels. We address the challenge of jointly selecting where and at which fidelity to evaluate to identify the highest-fidelity feasible Pareto frontier in this combined setting. From a unified information-theoretic perspective, we measure query utility by the information gain about this frontier, provided by an observation. Since this mutual information is intractable, we derive a variational lower bound using a mixture of under- and over-truncated approximations to the Pareto-consistent region. Multi-fidelity surrogate models propagate the information to arbitrary fidelities, yielding a cost-aware acquisition function without separate heuristics for fidelity selection or constraint handling. Experiments on synthetic, benchmark, and real-world problems demonstrate effectiveness across diverse objective, constraint, and fidelity settings.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Matsumoto, R., Ishikura, M., & Karasuyama, M. (2026). A Unified Information-Theoretic Approach to Constrained Multi-Fidelity Multi-Objective Bayesian Optimization. https://omanscience.com/en/articles/a-unified-information-theoretic-approach-to-constrained-multi-fidelity-multi-objective-bayesian-optimization
MLA 9
Matsumoto, Rikuto, et al. "A Unified Information-Theoretic Approach to Constrained Multi-Fidelity Multi-Objective Bayesian Optimization." https://omanscience.com/en/articles/a-unified-information-theoretic-approach-to-constrained-multi-fidelity-multi-objective-bayesian-optimization.
Chicago (author–date)
Matsumoto, Rikuto, Masanori Ishikura, and Masayuki Karasuyama. 2026. "A Unified Information-Theoretic Approach to Constrained Multi-Fidelity Multi-Objective Bayesian Optimization." https://omanscience.com/en/articles/a-unified-information-theoretic-approach-to-constrained-multi-fidelity-multi-objective-bayesian-optimization.
Harvard
Matsumoto, R., Ishikura, M. and Karasuyama, M. (2026) 'A Unified Information-Theoretic Approach to Constrained Multi-Fidelity Multi-Objective Bayesian Optimization', Available at: https://omanscience.com/en/articles/a-unified-information-theoretic-approach-to-constrained-multi-fidelity-multi-objective-bayesian-optimization.
Vancouver
Matsumoto R, Ishikura M, Karasuyama M. A Unified Information-Theoretic Approach to Constrained Multi-Fidelity Multi-Objective Bayesian Optimization. https://omanscience.com/en/articles/a-unified-information-theoretic-approach-to-constrained-multi-fidelity-multi-objective-bayesian-optimization
IEEE
R. Matsumoto, M. Ishikura, and M. Karasuyama, "A Unified Information-Theoretic Approach to Constrained Multi-Fidelity Multi-Objective Bayesian Optimization," https://omanscience.com/en/articles/a-unified-information-theoretic-approach-to-constrained-multi-fidelity-multi-objective-bayesian-optimization.