Research map / Probabilistic and scientific modeling / Bayesian optimization
Deferred Aggregation in Hierarchical Bayesian Optimization
Valentin Margraf, Jonas Hanselle, Julian Rodemann, Marcel Wever, Sebastian Vollmer, Eyke Hüllermeier
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes deferring aggregation to the decision level in hierarchical Bayesian optimization, where each GP hyperparameter sample proposes its own candidate that is then aggregated, instead of averaging models or acquisition functions.
Problem
Hierarchical Bayesian optimization marginalizes over Gaussian process hyperparameters by averaging models or acquisition functions early, which discards model disagreement information and is sensitive to outliers.
Approach
Each hyperparameter-conditioned model independently proposes a candidate, and the candidates are aggregated at the decision level rather than aggregating models or acquisition functions beforehand.
Closest papers by meaning
- The Bias-Variance Tradeoff in Data-Driven Optimization: A Local Misspecification Perspective (NeurIPS 2025 · similarity 0.87)
- Bayesian Uncertainty for Gradient Aggregation in Multi-Task Learning (ICML 2024 · similarity 0.86)
- Demystifying Linear MDPs and Novel Dynamics Aggregation Framework (ICLR 2024 · similarity 0.86)
- Contextual Optimization Under Model Misspecification: A Tractable and Generalizable Approach (ICML 2025 · similarity 0.85)
- Robust and Computation-Aware Gaussian Processes (NeurIPS 2025 · similarity 0.85)
- Stopping Bayesian Optimization with Probabilistic Regret Bounds (NeurIPS 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
