Accelerating evolutionary algorithms with Gaussian process fitness function models

By Dirk Büche, N. Schraudolph, Petros Koumoutsakos. IEEE Transactions on Systems Man and Cybernetics Part C (Applications and Reviews), 2005

351 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Theory and Mathematics

View Paper: https://www.semanticscholar.org/paper/a878f93255e5fd476a7a8d15706cbbc7bbfc88a8

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computational Theory and Mathematics

Citations in the corpus

Surrogate-Assisted Cooperative Swarm Optimization of High-Dimensional Expensive Problems (2017, methodology): “The most commonly used surrogate models include polynomial regression [19], also known as response surface methodology [19], support vector machines [20]–[22], ANNs [12], [23], [24], radial basis function (RBF) networks [25]–[29], and Gaussian processes (GPs), also referred as to Kriging or design a”
Data-Driven Surrogate-Assisted Multiobjective Evolutionary Optimization of a Trauma System (2016, background): “gates, such as linear, nonlinear, or polynomial repression models [31]; Kriging or Gaussian processes [32]–[38]; support vector machines [39]; radial basis function networks [40]–[42];”
Model-based methods for continuous and discrete global optimization (2017, methodology): “regression models such as polynomial regression or response surface methodology [18], support vector machines (SVM) [19], artificial neural networks [20], radial basis functions [21], or Gaussian process (GP) models, which are sometimes also referred to as DACE or Kriging [22, 23, 24, 25, 26] are th”
A Gaussian Process Surrogate Model Assisted Evolutionary Algorithm for Medium Scale Expensive Optimization Problems (2014, methodology): “1) GP modeling is a theoretically sound method for determining a much smaller number of free model parameters than many other surrogate modeling approaches [18], [19].”
Resampling Methods for Meta-Model Validation with Recommendations for Evolutionary Computation (2012, background): “While many machine learning toolboxes contain at least some of the mentioned resampling strategies, we would like to point out that our own R package mlr ( Bischl, 2010 ) contains all of the methods mentioned in this paper, including generic nested resampling, and an interface to many regression, cl”
Surrogate-assisted evolutionary computation: Recent advances and future challenges (2011, methodology): “Due to this property, Gaussian processes have increasingly been employed as surrogates in evolutionary single-and multi-objective optimization [41] [42] [43] [44].”
ParEGO: a hybrid algorithm with on-line landscape approximation for expensive multiobjective optimization problems (2006, methodology): “In the evolutionary algorithm community, response surface and Kriging methods have also been used within EAs, to model either the global landscape [ 4 ], [21], [29], [41], [50] or a local region of it [51], in order to reduce the number of expensive function evaluations that need to be carried out d”
Gaussian Processes for Regression and Optimisation (2007, background): “[8] in the following ways.”
Offline Data-Driven Evolutionary Optimization Using Selective Surrogate Ensembles (2019, background): “Infill criteria, including expected improvement [32], lower confidence bound (LCB) [33], [34], and”
Single- and multiobjective evolutionary optimization assisted by Gaussian random field metamodels (2006, methodology): “For a systematic study of the number of neighbors, we refer to [ 3 ].”