Kriging Is Well-Suited to Parallelize Optimization
Adaptation, learning, and optimizationPublished 1 January 2010Open access
David Ginsbourger, Rodolphe Le Riche, Laurent Carraro
Citations393
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
This work investigates a multi-points optimization criterion, the multipoints expected improvement (\(q-{\mathbb E}I\)), aimed at choosing several points at the same time, and proposes two classes of heuristic strategies meant to approximately optimize the Q-EI, and applies them to the classical Branin-Hoo test-case function.
Abstract
International audience
Keywords
Computer ScienceDecision Sciences
Particle swarm optimization
47,523 Citations2002James Kennedy, R.C. Eberhart
ScienceOptimization by Simulated Annealing
44,600 Citations1983Scott Kirkpatrick, C. D. Gelatt +1 more
A detailed analogy with annealing in solids provides a framework for optimization of the properties of very large and complex systems.
Springer series in statisticsThe Elements of Statistical Learning
24,344 Citations2001Trevor Hastie, J. Friedman +1 more
Choice Reviews OnlineNeural networks for pattern recognition
18,687 Citations1994
This is the first comprehensive treatment of feed-forward neural networks from the perspective of statistical pattern recognition, and is designed as a text, with over 100 exercises, to benefit anyone involved in the fields of neural computation and pattern recognition.
Neural Networks for Pattern Recognition
12,198 Citations1995Chris Bishop
The MIT Press eBooksGaussian Processes for Machine Learning
10,409 Citations2005Carl Edward Rasmussen, Christopher K. I. Williams
The book provides a long-needed, systematic and unified treatment of theoretical and practical aspects of GPs in machine learning, targeted at researchers and students in machine learning and applied statistics.
Journal of Global OptimizationEfficient Global Optimization of Expensive Black-Box Functions
7,799 Citations1998Donald R. Jones, Matthias Schonlau +1 more
This paper introduces the reader to a response surface methodology that is especially good at modeling the nonlinear, multimodal functions that often occur in engineering and shows how these approximating functions can be used to construct an efficient global optimization algorithm with a credible stopping rule.
Statistical ScienceDesign and Analysis of Computer Experiments
6,947 Citations1989Jerome Sacks, William J. Welch +2 more
Journal of the American Statistical AssociationSpline Models for Observational Data.
5,025 Citations1991Hans‐Georg Müller, Grace Wahba
Natural computing seriesIntroduction to Evolutionary Computing
4,175 Citations2003A. E. Eiben, James E. Smith
Journal of the Southern African Institute of Mining and MetallurgyA statistical approach to some basic mine valuation problems on the Witwatersrand
2,443 Citations1951D.G. Krige
Journal of Global OptimizationA Taxonomy of Global Optimization Methods Based on Response Surfaces
2,137 Citations2001Donald R. Jones
This paper presents a taxonomy of existing approaches for using response surfaces for global optimization, illustrating each method with a simple numerical example that brings out its advantages and disadvantages.
Springer series in statisticsThe Design and Analysis of Computer Experiments
2,135 Citations2003Thomas J. Santner, Brian J. Williams +1 more
Journal of Optimization Theory and ApplicationsLipschitzian optimization without the Lipschitz constant
1,987 Citations1993Donald R. Jones, C.D. Perttunen +1 more
Physics of Life ReviewsAnt colony optimization: Introduction and recent trends
1,287 Citations2005Christian Blum
This work deals with the biological inspiration of ant colony optimization algorithms and shows how this biological inspiration can be transfered into an algorithm for discrete optimization, and presents some of the nowadays best-performing ant colonies optimization variants.
IEEE Transactions on Evolutionary ComputationParEGO: a hybrid algorithm with on-line landscape approximation for expensive multiobjective optimization problems
1,175 Citations2006Joshua Knowles
Results show that NSGA-II, a popular multiobjective evolutionary algorithm, performs well compared with random search, even within the restricted number of evaluations used.
Aston Publications Explorer (Aston University)Gaussian Processes for Regression
1,142 Citations1995Christopher K. I. Williams, Carl Edward Rasmussen
This paper investigates the use of Gaussian process priors over functions, which permit the predictive Bayesian analysis for fixed values of hyperparameters to be carried out exactly using matrix operations.
AIAA JournalUse of Kriging Models to Approximate Deterministic Computer Models
832 Citations2005Jay D. Martin, Timothy W. Simpson
This paper compares Maximum Likelihood Estimation (MLE) and Cross-Validation (CV) parameter estimation methods for selecting a kriging model’s parameters given its form and and an R 2 of prediction and the corrected Akaike Information Criterion for assessing the quality of the created kriged model, permitting the comparison of different forms of a k Riging model.
Reliability Engineering & System SafetyBayesian analysis of computer code outputs: A tutorial
773 Citations2006Anthony O’Hagan
This tutorial is to introduce the more general reader to the Bayesian approach to quantifying, analysing and reducing uncertainty in the application of complex process models.
IEEE Transactions on Evolutionary ComputationSingle- and multiobjective evolutionary optimization assisted by Gaussian random field metamodels
734 Citations2006Michael Emmerich, Kyriakos C. Giannakoglou +1 more
The extensive use of the uncertainty information of predictions for screening the candidate solutions makes it possible to significantly reduce the computational cost of singleand multiobjective EA.
Journal of Global OptimizationGlobal Optimization of Stochastic Black-Box Systems via Sequential Kriging Meta-Models
636 Citations2006D. Huang, Theodore T. Allen +2 more
The proposed method is based on a kriging meta-model that provides a global prediction of the objective values and a measure of prediction uncertainty at every point and has excellent consistency and efficiency in finding global optimal solutions.
International Conference on Artificial Intelligence and StatisticsClasses of kernels for machine learning: a statistics perspective
633 Citations2002Marc G. Genton
The spectral representation of the various classes of kernels is described and a discussion on the characterization of nonlinear maps that reduce nonstationary kernels to either stationarity or local stationarity is discussed.
IEEE Transactions on Pattern Analysis and Machine IntelligenceAn active testing model for tracking roads in satellite images
498 Citations1996Donald Geman, Bruno Jedynak
A new approach for tracking roads from satellite images, and thereby illustrate a general computational strategy for tracking 1D structures and other recognition tasks in computer vision, related to recent work in active vision and motivated by the "divide-and-conquer" strategy of parlour games.
Structural and Multidisciplinary OptimizationSequential kriging optimization using multiple-fidelity evaluations
431 Citations2006D. Huang, Theodore T. Allen +2 more
The proposed extension of the sequential kriging optimization method, surrogate systems are exploited to reduce the total evaluation cost and manifests sensible search patterns, robust performance, and appreciable reduction in total evaluation costs as compared to the original method.
Engineering OptimizationExploration of Metamodeling Sampling Criteria for Constrained Global Optimization
421 Citations2002Michael J. Sasena, Panos Y. Papalambros +1 more
This paper focuses on a particular algorithm, Efficient Global Optimization (EGO), that uses kriging metamodels and several infill sampling criteria are reviewed, namely criteria for selecting design points at which the true functions are evaluated.
Computer experiments and global optimization
379 Citations1997William J. Welch, Matthias Schonlau
This thesis considers the problem of finding the global optimum of the response with few function evaluations and presents strategies to conduct the optimization in stages and for optimization subject to constraints on additional response variables.
Flexibility and Efficiency Enhancements for Constrained Global Design Optimization with Kriging Approximations
352 Citations2002Michael J. Sasena
Handbook of statistics9 Computer experiments
308 Citations1996James R. Koehler, Art B. Owen
This chapter presents and compares two statistical approaches to computer experiments and introduces randomness by modeling the function, f, as a realization of a Gaussian process.
Journal of Global OptimizationAn informational approach to the global optimization of expensive-to-evaluate functions
306 Citations2008Julien Villemonteix, Emmanuel Vázquez +1 more
This paper introduces minimizers entropy as a new Kriging-based criterion for the sequential choice of points at which the function should be evaluated, based on stepwise uncertainty reduction and is extended to robust optimization problems, where both the factors to be tuned and the function evaluations are corrupted by noise.
Lecture notes in computer scienceMultiobjective Optimization on a Limited Budget of Evaluations Using Model-Assisted $\mathcal{S}$ -Metric Selection
218 Citations2008Wolfgang Ponweiser, Tobias Wagner +2 more
This paper provides a review of contemporary multiobjective approaches based on the singleobjective meta-model-assisted 'Efficient Global Optimization' (EGO) procedure and describes their main concepts and introduces a new EGO-based MOOA, which utilizes the $\mathcal{S}$-metric or hypervolume contribution to decide which solution is evaluated next.
Evolution strategies assisted by Gaussian processes with improved preselection criterion
121 Citations2003Holger Ulmer, Felix Streichert +1 more
This work proposes a model assisted evolution strategy, which uses a Gaussian process approximation model to preselect the most promising solutions, and achieves better results than standard evolutionary optimization approaches with less fitness evaluations.
VTechWorks (Virginia Tech)Parallel global aircraft configuration design space exploration
44 Citations2001Chuck Baker, Layne T. Watson +3 more
9th AIAA/ISSMO Symposium on Multidisciplinary Analysis and OptimizationGlobal Optimization of Problems with Disconnected Feasible Regions via Surrogate Modeling
41 Citations2002Michael J. Sasena, Panos Y. Papalambros +1 more
This work proposes taking advantage of superEGO’s flexibility to design alternative search strategies that locate multiple feasible regions in a new way, and was successfully applied to two analytical examples and required far fewer function calls than three competing techniques.
HAL (Le Centre pour la Communication Scientifique Directe)Radial Basis Functions and Kriging Metamodels for Aerodynamic Optimization
41 Citations2007Praveen Chandrashekarappa, Régis Duvigneau
This work considers data-fitting models, particularly radial basis functions and kriging, which have parameters which must be selected carefully to ensure good accuracy and are implemented in the shape optimization platform FAMOSA.
10th AIAA/ISSMO Multidisciplinary Analysis and Optimization ConferenceA Monte Carlo Simulation of the Kriging Model
37 Citations2004Jay D. Martin, Timothy W. Simpson
HAL (Le Centre pour la Communication Scientifique Directe)A Multi-points Criterion for Deterministic Parallel Global Optimization based on Kriging
34 Citations2007David Ginsbourger, Rodolphe Le Riche +1 more
Quality and Reliability Engineering InternationalAn Adaptive Sequential Procedure for Efficient Optimization of the Sheet Metal Spinning Process
23 Citations2005Nadine Henkenjohann, Roland Göbel +2 more
An adaptive sequential optimization procedure (ASOP) is presented to cope with the problems of complex processes in order to guarantee an efficient optimization of such complex processes.
Structural and Multidisciplinary Optimization10th AIAA/ISSMO Multidisciplinary Analysis and Optimization Conference, Albany, NY, 30 August – 1 September 2004
15 Citations2003Achille Messac
HAL (Le Centre pour la Communication Scientifique Directe)MULTIPLES MÉTAMODÈLES POUR L'APPROXIMATION ET L'OPTIMISATION DE FONCTIONS NUMÉRIQUES MULTIVARIABLES
13 Citations2009David Ginsbourger
Evaluation d'un projet minier : approche bayésienne et options réelles
7 Citations2004Sarah Goria
HAL (Le Centre pour la Communication Scientifique Directe)Optimisation de fonctions coûteuses<br />Modèles gaussiens pour une utilisation efficace du budget d'évaluations : théorie et pratique industrielle
2 Citations2008Julien Villemonteix
Cette travail traite d'algorithmes d'optimisation specifiques a ce contexte pour lequel la plupart des methodes classiques sont inadaptees est d'exploiter les proprietes des processus gaussiens and du krigeage pour construire une approximation peu couteuse de the fonction a optimiser.