Principled Bayesian Optimization in Collaboration with Human Experts
Wenjie Xu, Masaki Adachi, Colin N. Jones, Michael A. Osborne
Abstract
Bayesian optimisation for real-world problems is often performed interactively with human experts, and integrating their domain knowledge is key to accelerate the optimisation process. We consider a setup where experts provide advice on the next query point through binary accept/reject recommendations (labels). Experts' labels are often costly, requiring efficient use of their efforts, and can at the same time be unreliable, requiring careful adjustment of the degree to which any expert is trusted. We introduce the first principled approach that provides two key guarantees. (1) Handover guarantee: similar to a no-regret property, we establish a sublinear bound on the cumulative number of experts' binary labels. Initially, multiple labels per query are needed, but the number of expert labels required asymptotically converges to zero, saving both expert effort and computation time. (2) No-harm guarantee with data-driven trust level adjustment: our adaptive trust level ensures that the convergence rate will not be worse than the one without using advice, even if the advice from experts is adversarial. Unlike existing methods that employ a userdefined function that hand-tunes the trust level adjustment, our approach enables data-driven adjustments. Real-world applications empirically demonstrate that our method not only outperforms existing baselines, but also maintains robustness despite varying labelling accuracy, in tasks of battery design with human experts.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
2 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- Chain-of-Thought Prompting Elicits Reasoning in Large Language Models cites Multitask Prompted Training Enables Zero-Shot Task Generalization
- Chain-of-Thought Prompting Elicits Reasoning in Large Language Models cites Training language models to follow instructions with human feedback
- Training language models to follow instructions with human feedback cites Multitask Prompted Training Enables Zero-Shot Task Generalization
- Human-LLM Collaborative Feature Engineering for Tabular Data cites Training language models to follow instructions with human feedback
Cited by top-tier papers2
- Unleashing LLMs in Bayesian Optimization: Preference-Guided Framework for Scientific DiscoveryXinzhe Yuan, Zhuo Chen, Jianshu Zhang, Huan Xiong et al.ICLR 2026 · 7 citations
- Human-LLM Collaborative Feature Engineering for Tabular DataZhuoyan Li, Aditya Bansal, Jinzhao Li, Shishuang He et al.ICLR 2026 · 2 citations
Builds on22
- Training language models to follow instructions with human feedbackLong Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida et al.NeurIPS 2022 · 24,707 citations
- Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma et al.NeurIPS 2022 · 22,562 citations
- Multitask Prompted Training Enables Zero-Shot Task GeneralizationVictor Sanh, Albert Webson, Colin Raffel, Stephen H. Bach et al.ICLR 2022 · 1,976 citations
- Constrained Efficient Global Optimization of Expensive Black-box FunctionsWenjie Xu, Yuning Jiang, Bratislav Svetozarevic, Colin N. JonesICML 2023 · 1,916 citations
- AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated PromptsTaylor Shin, Yasaman Razeghi, Robert L. Logan IV, Eric Wallace et al.EMNLP 2020 · 1,162 citations
Related papers
- Human-AI Collaborative Bayesian OptimisationArun Kumar A. V., Santu Rana, Alistair Shilton, Svetha VenkateshNeurIPS 2022 · 24 citations
- Incorporating Expert Priors into Bayesian Optimization via Dynamic Mean DecayChongqi Qu, Meiqin Liu, Jian Lan, Shanling Dong et al.ICLR 2026
- Aggregating Binary Judgments Ranked by AccuracyDaniel Halpern, Gregory Kehne, Dominik Peters, Ariel D. Procaccia et al.AAAI 2021 · 1 citation
- Collaborative Bayesian Optimization with Fair RegretRachael Hwee Ling Sim, Yehong Zhang, Bryan Kian Hsiang Low, Patrick JailletICML 2021 · 26 citations
- A General Framework for User-Guided Bayesian OptimizationCarl Hvarfner, Frank Hutter, Luigi NardiICLR 2024 · 21 citations
