scientific article; zbMATH DE number 7049769

zbMath1484.68179arXiv1901.03357MaRDI QIDQ4633069

Angela P. Schoellig, Andreas Krause, Felix Berkenkamp

Publication date: 2 May 2019

Full work available at URL: https://arxiv.org/abs/1901.03357

Title: zbMATH Open Web Interface contents unavailable due to conflicting licenses.

zbMATH Keywords

no regretBayesian optimizationunknown hyperparametersbanditsreproducing-kernel Hilbert space (RKHS)

Mathematics Subject Classification ID

Bayesian inference (62F15) Nonconvex programming, global optimization (90C26) Learning and adaptive systems in artificial intelligence (68T05)

Related Items

AutoDiagnosis: Automatic Data-Driven Configuration of an Automotive Fault Diagnosis Algorithm Using Noisy Two-Stage Optimization, Safe global optimization of expensive noisy black-box functions in the \(\delta \)-Lipschitz framework, Unnamed Item, An efficient modified Hyperband and trust-region-based mode-pursuing sampling hybrid method for hyperparameter optimization, Bayesian optimization with safety constraints: safe and automatic parameter tuning in robotics, \textsc{GoSafeOpt}: scalable safe exploration for global optimization of dynamical systems, Unnamed Item, Modeling and Active Learning for Experiments with Quantitative-Sequence Factors, High-dimensional Bayesian optimization with projections using quantile Gaussian processes, Unnamed Item, Unnamed Item

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• The Knowledge-Gradient Policy for Correlated Normal Beliefs
• Support Vector Machines
• Information Consistency of Nonparametric Gaussian Process Methods
• Learning to Optimize via Information-Directed Sampling
• Information-Theoretic Regret Bounds for Gaussian Process Optimization in the Bandit Setting
• Convergence rates of efficient global optimization algorithms