Evolution strategies – A comprehensive introduction

By Hans-Georg Beyer, Hans-Paul Schwefel. 2002

2,830 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Theory and Mathematics

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

A Survey on Neural Architecture Search (2019, methodology): “They propose to use the (1+λ)-evolutionary strategy (λ = 2) (Beyer and Schwefel, 2002) approach to guide the evolution where mutation and selection operators are applied in a loop until termination.”
One Pixel Attack for Fooling Deep Neural Networks (2017, methodology): “The DE utilized in this paper belongs to a big class of algorithms called evolutionary strategies [47] which includes other variants, such as adaptive DE [48] and covariance matrix”
DEAP: evolutionary algorithms made easy (2012, methodology): “…implementation of any type of EA, including genetic algorithms (Mitchell, 1998), genetic programming (Banzhaf et al., 1998), evolution strategies (Beyer and Schwefel, 2002), covariance matrix adaptation evolution strategy (Hansen and Ostermeier, 2001), particle swarm optimization (Kennedy and…”
Emperor penguin optimizer: A bio-inspired algorithm for engineering problems (2018, background): “Apart from these, some of the other popular evolutionary-based algorithms are Genetic Programming (GP) [21], Evolution Strategy (ES) [22], and Biogeography-based Optimizer (BBO) [23].”
Modern Evolution Strategies for Creativity: Fitting Concrete Images and Abstract Concepts (2021, methodology): “Evolution Strategies (ES) [3, 4] has been applied to optimization problems for a long period of time.”
Optimizing connection weights in neural networks using the whale optimization algorithm (2016, background): “Differential evolution (DE) (Storn and Price 1997; Price et al 2006; Das and Suganthan 2011) and evolution strategy (ES) (Beyer and Schwefel 2002) are other examples of evolutionary algorithms.”
Evolution Strategies (2018, background): “More comprehensive historical overviews can be found elsewhere [6, 7].”
Evolutionary tuning of multiple SVM parameters (2005, positive): “Evolution strategies (ES, [1]) are one of the main branches of evolutionary algorithms, i.e., a class of iterative, direct, randomized optimization methods mimicking principles of neo-Darwinian evolution theory.”
A Multi-Facet Survey on Memetic Computation (2011, background): “Typical population-based search frameworks including genetic algorithm (GA) [8], evolution strategy (ES) [9], evolutionary programming [10], genetic programming [11], differential evolution (DE) [12], estimation of distribution algorithm (EDA) [13], ant colony optimization (ACO) [14], particle swarm”
Covariance Matrix Adaptation for Multi-objective Optimization (2007, methodology): “In this section we combine the well known (1+ λ )-selection scheme of evolution strategies (Rechenberg, 1973; Schwefel, 1995; Beyer and Schwefel, 2002) with the covariance matrix adaptation.”
SMS-EMOA: Multiobjective selection based on dominated hypervolume (2007, methodology): “3 We invoked one step size for each search direction, two randomly chosen parents to generate one offspring, intermediate recombination on the step sizes, discrete recombination on the object parameters and a simple Gaussian mutation operator for step sizes and object parameters according to Beyer a”
Particle Swarm Optimization and Intelligence: Advances and Applications (2010, methodology): “These characteristics render evolution strategies a more appealing approach for solving numerical optimization problems than the evolutionary algorithms presented in previous sections (Beyer, 2001; Beyer & Schwefel, 2002; Hansen & Ostermeier, 2001; Schwefel, 1995).”