analiza aiqbench
This research addresses a critical reliability gap in multi-objective Bayesian optimization by adapting nonstationary Gaussian processes to better handle sequential decision-making under uncertainty. The proposed MOLRN-BO framework combines shared spectral surrogates with local-global search policies, demonstrating superior robustness and hypervolume performance on standard benchmarks compared to existing baselines. For practitioners deploying complex optimization pipelines, this work offers a more trustworthy surrogate model that mitigates the risk of overfitting while maintaining global exploration capabilities.
Adapting Nonstationary Multi-output Gaussian Processes to Bayesian Optimization
arXiv:2609.32464v1 Announce Type: new Abstract: Multi-objective Bayesian optimization (MOBO) commonly relies on independent Gaussian processes (GPs) with stationary kernels, limiting its ability to represent nonstationary structure and share information between objectives. However, expressive nonstationary GPs do not necessarily make reliable BO decisions. We study this mismatch for the multi-output low-rank nonstationary (MO-LRN) GP: strong training fit can coexist with large off-design errors and optimistic acquisition predictions. We introduce MOLRN-BO, which combines a regularized shared-spectral surrogate with objective-specific residuals, prequential mean correction and tempered covariance scaling, and Pareto-local qLogEHVI optimization with periodic global search. Experiments on 12 deterministic bi-objective benchmarks show that MOLRN-BO substantially improves upon the original MO-LRN and achieves the best average problem ranks for final normalized hypervolume and normalized inverted generational distance among nine evaluated algorithms. It also achieves the strongest adverse-tail performance while remaining competitive with the leading baselines in anytime optimization. Ablation studies further show that the shared spectral construction improves off-design prediction, the local--global decision policy improves optimization performance, and hierarchical calibration reduces systematic candidate bias. These results demonstrate that nonstationary multi-output surrogates can deliver strong and robust MOBO performance when their structure and use are explicitly adapted to the demands of sequential optimization.
Abstract:Multi-objective Bayesian optimization (MOBO) commonly relies on independent Gaussian processes (GPs) with stationary kernels, limiting its ability to represent nonstationary structure and share information between objectives. However, expressive nonstationary GPs do not necessarily make reliable BO decisions. We study this mismatch for the multi-output low-rank nonstationary (MO-LRN) GP: strong training fit can coexist with large off-design errors and optimistic acquisition predictions. We introduce MOLRN-BO, which combines a regularized shared-spectral surrogate with objective-specific residuals, prequential mean correction and tempered covariance scaling, and Pareto-local qLogEHVI optimization with periodic global search. Experiments on 12 deterministic bi-objective benchmarks show that MOLRN-BO substantially improves upon the original MO-LRN and achieves the best average problem ranks for final normalized hypervolume and normalized inverted generational distance among nine evaluated algorithms. It also achieves the strongest adverse-tail performance while remaining competitive with the leading baselines in anytime optimization. Ablation studies further show that the shared spectral construction improves off-design prediction, the local--global decision policy improves optimization performance, and hierarchical calibration reduces systematic candidate bias. These results demonstrate that nonstationary multi-output surrogates can deliver strong and robust MOBO performance when their structure and use are explicitly adapted to the demands of sequential optimization.
Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
arXiv:2609.32464 [cs.LG]
(or arXiv:2609.32464v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2609.32464 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 291 cuvinte
Subiecte conexe
Joint Surrogate Learning of Objectives, Constraints, and Sensitivities for Efficient Multi-objective Optimization of Neural Dynamical Systems
arXiv · 30 sept. 2026
[AINews] not much happened today
Latent Space · 18 sept. 2026
Regime-Adaptive Bayesian Optimization via Dirichlet Process Mixtures of Gaussian Processes
arXiv · 29 iul. 2026
Exploiting Hierarchical Controller Structure in Contextual Parameter Learning for Humanoid Loco-Manipulation
arXiv · 6 oct. 2026