Bayesian Optimization

Follow this topic Ask about this topic

Bayesian optimization studies how to find good inputs to an expensive or unknown process—such as a simulation, experiment, or model configuration—using as few evaluations as possible. It typically fits a probabilistic surrogate, often a Gaussian process, then uses an acquisition function to balance trying promising inputs with exploring uncertain ones. Current approaches extend this loop with trust regions, multi-fidelity data, constraints, multiple objectives, changing conditions, and human or language-model guidance. A central challenge is choosing models and search strategies that remain reliable in high-dimensional or structured spaces without making inference and candidate selection too costly; theoretical guarantees do not always predict practical performance.

Latest papers

243 papers45 papers in the last four weeks, up 36% on the four weeks before. 0.3% of all new papers.

Goal-Oriented Lower-Tail Calibration of Gaussian Processes for Bayesian Optimization
May 19, 2026Aurélien Pion, Emmanuel VazquezPost-Hoc Calibration Bayesian Optimization
Transvalor S.A., Biot, France · Univ. Paris-Saclay, CNRS, CentraleSup´elec, L2S, Gif-sur-Yvette, France
Embedding by Elicitation: Dynamic Representations for Bayesian Optimization of System Prompts
May 18, 2026Zhiyuan Jerry Lin, Benjamin Letham, Samuel Dooley +2Bayesian Optimization Large Language Model-Guided Optimization
Meta
Automated Kernel Discovery Towards Understanding High-dimensional Bayesian Optimization
May 18, 2026Taeyoung Yun, Woocheol Shin, Inhyuck Song +2Bayesian Optimization Large Language Model-Guided Optimization
1Korea Advanced Institute of Science and Technology (KAIST)
Unleashing LLMs in Bayesian Optimization: Preference-Guided Framework for Scientific Discovery
May 18, 2026Xinzhe Yuan, Zhuo Chen, Jianshu Zhang +4Bayesian Optimization Large Language Model-Guided Optimization
Shanghai Artificial Intelligence Laboratory, Shanghai, China · Shanghai Jiao Tong University, Shanghai, China · Harbin Institute of Technology, Harbin, China
BoLT: A Benchmark to Democratize Black-box Optimization Research for Expensive LLM Tasks
May 16, 2026Ruth Wan Theng Chew, Zhiliang Chen, Apivich Hemachandra +1Bayesian Optimization Benchmark Design
National University of Singapore
Safe Bayesian Optimization for Uncertain Correlation Matrices in Linear Models of Co-Regionalization
May 13, 2026Jannis Lübsen, Annika EichlerBayesian Optimization Gaussian Processes
Institute of Control Systems, Hamburg University of Technology, Hamburg, Germany · Institute of Control Systems, Hamburg University of Technology · Deutsches Elektronen-Synchrotron, Hamburg, Germany
Kernel-based guarantees for nonlinear parametric models in Bayesian optimization
May 13, 2026Rafael OliveiraBayesian Optimization Adaptive Sampling
The Commonwealth Scientific and Industrial Research Organisation (CSIRO) Sydney, Australia
Efficient Conditioning Why Pseudo Observation Batch Bayesian Optimization Works When It Does not
May 12, 2026Kumbha Nagaswetha, Rabi PathakSurrogate Modeling Bayesian Optimization
Elicitation-Augmented Bayesian Optimization
May 12, 2026Alvar Haltia, Ville Hyvönen, Samuel KaskiBayesian Optimization Human-in-the-Loop Evaluation
Aalto University · University of Helsinki · Aalto University, University of Manchester
Online Sharp-Calibrated Bayesian Optimization
May 11, 2026Marshal Arijona Sinaga, Julien Martinelli, Teemu Turpeinen +1Bayesian Optimization Uncertainty Calibration
ELLIS Institute Finland · Aalto University · University of Manchester
Regret Analysis of Guided Diffusion for Black-Box Optimization over Structured Inputs
May 11, 2026Masaki Adachi, Anita Yang, Yakun Wang +1Bayesian Optimization Black-Box Optimization
Toyota Motor Corporation · Lattice Lab · University of Bristol
Many Needles in a Haystack: Active Hit Discovery for Perturbation Experiments
May 11, 2026Andrea Rubbi, Arpit Merchant, Samuel Ogden +4Bayesian Optimization Bayesian Experimental Design
Department of Computer Science and Technology, University of Cambridge, Cambridge, UK · Cambridge Center for AI in Medicine, University of Cambridge, Cambridge, UK · MediaTek Research, Cambridge, UK +1
Bayesian Optimization with Structured Measurements: A Vector-Valued RKHS Framework
May 10, 2026Wenbin Wang, Colin N. JonesKernel Ridge Regression Bayesian Optimization
Automatic Control Laboratory, EPFL
ADKO: Agentic Decentralized Knowledge Optimization
May 8, 2026Lucas Nerone Rillo, Zhanhong Jiang, Nastaran Saadati +4Multi-Agent System Optimization AI Agents for Scientific Discovery
Iowa State University · New York University
Open-Ended Task Discovery via Bayesian Optimization
May 8, 2026Masaki Adachi, Yuta Suzuki, Juliusz ZiomekBayesian Optimization
Lattice Lab · Toyota Motor Corporation · Machine Learning Research Group +1
Ensemble Distributionally Robust Bayesian Optimisation with Continuous Context
May 8, 2026Tigran Ramazyan, Denis DerkachBayesian Optimization Distributionally Robust Optimization
Faculty of Computer Science, HSE University, Pokrovsky Boulevard 11, Moscow, 109028, Moscow, Russia.
ORTHOBO: Orthogonal Bayesian Hyperparameter Optimization
May 7, 2026Maresa Schröder, Pascal Janetzky, Michael Klar +1Bayesian Optimization Variance Reduction
LMU Munich · Munich Center for Machine Learning · Bosch Center for Artificial Intelligence
Decoupled PFNs: Identifiable Epistemic-Aleatoric Decomposition via Structured Synthetic Priors
May 7, 2026Richard Bergna, Stefan Depeweg, José Miguel Hernández-LobatoUncertainty Quantification Bayesian Optimization
University of Cambridge · 2Siemens AG
In-Context Black-Box Optimization with Unreliable Feedback
May 7, 2026Nicolas Samuel Blumer, Julien Martinelli, Samuel KaskiBayesian Optimization Black-Box Optimization
ELLIS Institute Finland · Aalto University · University of Manchester
Meta-learning for sample-efficient Bayesian optimisation of fed-batch processes
May 6, 2026Becky Langdon, Gabriel D. Patrón, Chrysoula D. Kappatou +6Meta-Learning Bayesian Optimization
Department of Computing, Imperial College London, United Kingdom · BASF SE, Ludwigshafen, Germany · School of Mathematical Sciences, Lancaster University, United Kingdom +1
Regime-Conditioned Evaluation in Multi-Context Bayesian Optimization
May 6, 2026Noel ThomasCausal Effect Estimation Conditional Average Treatment Effect Estimation
Mohamed bin Zayed University of Artificial Intelligence Abu Dhabi, UAE
Elicitation Matters: How Prompts and Query Protocols Shape LLM Surrogates under Sparse Observations
May 6, 2026Ge Lei, Samuel J. CooperSurrogate Modeling Bayesian Optimization
Dyson School of Design Engineering Imperial College London Exhibition Road, London SW7 2AZ
Caliper-in-the-Loop: Black-Box Optimization for Hyperledger Fabric Performance Tuning
May 4, 2026Yash Madhwal, Arseny Bolotnikov, Mark Prikhno +5Bayesian Optimization Black-Box Optimization
Skolkovo Institute of Science and Technology, Moscow, Russia · HSE University, Moscow, Russia · Sberbank PJSC, Moscow, Russia +4
Inducing Permutation Invariant Priors in Bayesian Optimization for Carbon Capture and Storage Applications
May 4, 2026Sofianos Panagiotis Fotias, Vassilis GaganisBayesian Optimization Gaussian Processes
School of Mining and Metallurgical Engineering, National Technical University of Athens, Athens, 15773, Greece
Bayesian Optimization in Linear Time
Apr 30, 2026Jesse Schneider, William J. WelchBayesian Optimization Black-Box Optimization
Department of Statistics, University of British Columbia, Vancouver, BC V6T 1Z4, Canada
Human-in-the-Loop Meta Bayesian Optimization for Fusion Energy and Scientific Applications
Apr 30, 2026Ricardo Luna Gutierrez, Sahand Ghorbanpour, Ejaz Rahman +5Meta-Learning Bayesian Optimization
1Hewlett Packard Enterprise · University of Rochester
Categorical Optimization with Bayesian Anchored Latent Trust Regions for Structural Design under High-Dimensional Uncertainty
Apr 28, 2026Zhangyong Liang, Jie Hou, Huanhuan Gao +1Stochastic Optimization Surrogate-Assisted Optimization
National Center for Applied Mathematics, Tianjin University, Weijin Road 92, 300072, Tianjin, China · School of Mechanical Engineering, Northwestern Polytechnical University, Youyixi Road 127, 710072, Xi’an, China · School of Mechanical and Aerospace Engineering, Jilin University, Renmin Street 5988, 130025, Changchun, China +1
Feasible-First Exploration for Constrained ML Deployment Optimization in Crash-Prone Hierarchical Search Spaces
Apr 27, 2026Christian LysenstøenBayesian Optimization Black-Box Optimization
Department of Electrical Engineering and Computer Sciences University of California, Berkeley
A Finite Time Analysis of Thompson Sampling for Bayesian Optimization with Preferential Feedback
Apr 27, 2026Joseph Lazzaro, Davide Buffelli, Da-shan Shiu +1Thompson Sampling Pairwise Preference Evaluation
Imperial College London · MediaTek Research
Rethinking Trust Region Bayesian Optimization in High Dimensions
Apr 24, 2026Wei-Ting Tang, Joel A. PaulsonBayesian Optimization Black-Box Optimization
University of Wisconsin–Madison

May 19, 2026J/K move · Enter open · S save

Goal-Oriented Lower-Tail Calibration of Gaussian Processes for Bayesian Optimization

Aurélien Pion, Emmanuel Vazquez

Transvalor S.A., Biot, France · Univ. Paris-Saclay, CNRS, CentraleSup´elec, L2S, Gif-sur-Yvette, France

Post-Hoc Calibration Bayesian Optimization Gaussian Processes Uncertainty Calibration

Open paper AskPDF arXiv

Gaussian process (GP) predictive distributions are commonly used in Bayesian optimization (BO) to guide the selection of evaluation points for expensive objective functions. The choice of kernel and hyperparameters has a strong influence on the exploration--exploitation trade-off. For minimization, sampling criteria such as expected improvement (EI) depend on both the probability mass below the current best value and the shape of the predictive distribution in this region. This article studies goal-oriented calibration of GP predictive distributions below a low threshold

t

in the noiseless setting, for standard GP models with hyperparameters selected by maximum likelihood. We consider two complementary forms of calibration below

t

for inputs distributed according to a reference measure

μ

: occurrence calibration over the design space and thresholded

μ

-calibration on sublevel sets of the form

\{x\in\mathbb{X}, f(x)\le t\}

. We propose tcGP, a post-hoc method that combines these two forms of calibration for GP predictive distributions below

t

. With fixed GP hyperparameters, the exact EI sampling criterion based on tcGP generates a sequence of evaluation points that is dense in the design space. Experiments on standard benchmarks show improved lower-tail calibration and BO performance relative to standard GP models and globally calibrated GP models.