A supermartingale approach to Gaussian process based sequential design of experiments

DOI10.3150/18-BEJ1074zbMath1428.62369arXiv1608.01118OpenAlexW2489204415MaRDI QIDQ2325344

François Bachoc, Julien Bect, David Ginsbourger

Publication date: 25 September 2019

Published in: Bernoulli (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1608.01118

zbMATH Keywords

convergenceactive learningsequential design of experimentssupermartingalestepwise uncertainty reductionuncertainty functional

Mathematics Subject Classification ID

Gaussian processes (60G15) Learning and adaptive systems in artificial intelligence (68T05) Generalizations of martingales (60G48) Sequential statistical design (62L05)

Related Items

Adaptive design for Gaussian process regression under censoring, Bayesian Optimization with Expensive Integrands, Sequential Construction and Dimension Reduction of Gaussian Processes Under Inequality Constraints, Technical note—Knowledge gradient for selection with covariates: Consistency and computation, Uncertainty Quantification and Experimental Design for Large-Scale Linear Inverse Problems under Gaussian Process Priors, Adaptive spatial designs minimizing the integrated Bernoulli variance in spatial logistic regression models -- with an application to benthic habitat mapping, Moderate deviations inequalities for Gaussian process regression, Bayesian Quadrature, Energy Minimization, and Space-Filling Design, Finite-Dimensional Gaussian Approximation with Linear Inequality Constraints, Learning excursion sets of vector-valued Gaussian random fields for autonomous ocean sampling, Composite likelihood estimation for a Gaussian process under fixed domain asymptotics, Gaussian process optimization with failures: classification and convergence proof, Expected improvement for expensive optimization: a review, A Bayesian optimization approach to find Nash equilibria, Data-driven stochastic inversion via functional quantization, Parallel Gaussian process surrogate Bayesian inference with noisy likelihood evaluations, Sequential Bayesian optimal experimental design for structural reliability analysis, Locally induced Gaussian processes for large-scale simulation experiments, Maximum likelihood estimation for Gaussian processes under inequality constraints, Unnamed Item

Uses Software

• EGO

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Learning functions and approximate Bayesian computation design: ABCD
• A Bayesian approach to constrained single- and multi-objective optimization
• Probability in Banach spaces. Isoperimetry and processes
• Sequential design of computer experiments for the estimation of a probability of failure
• An informational approach to the global optimization of expensive-to-evaluate functions
• On degeneracy and invariances of random fields paths with applications in Gaussian process modelling
• Convergence properties of the expected improvement algorithm with fixed mean and covariance functions
• Functional analysis, Sobolev spaces and partial differential equations
• Changes in utility as information
• Bayes-Hermite quadrature
• Efficient global optimization of expensive black-box functions
• Interpolation of spatial data. Some theory for kriging
• Estimating functions evaluated by simulation: a Bayesian/analytic approach
• The design and analysis of computer experiments.
• Average-case analysis of numerical problems
• Design and analysis of computer experiments. With comments and a rejoinder by the authors
• A note on the measurability of the pseudo-inverse
• Univariate interpolation by exponential functions and Gaussian RBFs for generic sets of nodes
• Jensen's inequality for a convex vector-valued function on an infinite-dimensional space
• Gaussian process surrogates for failure detection: a Bayesian experimental design approach
• Examples of inconsistency in optimization by expected improvement
• Stochastic processes with sample paths in reproducing kernel Hilbert spaces
• The Knowledge-Gradient Policy for Correlated Normal Beliefs
• Bayesian Adaptive Reconstruction of Profile Optima and Optimizers
• The Correlated Knowledge Gradient for Simulation Optimization of Continuous Parameters using Gaussian Process Regression
• A Knowledge-Gradient Policy for Sequential Information Collection
• Level Sets and Extrema of Random Processes and Fields
• Pushing the Limits of Contemporary Statistics: Contributions in Honor of Jayanta K. Ghosh
• Bayesian Subset Simulation
• Statistics for Spatial Data
• Information-Theoretic Regret Bounds for Gaussian Process Optimization in the Bandit Setting
• Probabilistic numerics and uncertainty in computations
• Convergence rates of efficient global optimization algorithms
• Theory of Random Sets
• Uncertainty, Information, and Sequential Experiments
• Probability Theory