A Comparative Analysis of Selection Schemes Used in Genetic Algorithms

By David E. Goldberg, Kalyanmoy Deb. 1990

How researchers see this paper

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

In Evolutionary Computation

Citations in the corpus

AutoML-Zero: Evolving Machine Learning Algorithms From Scratch (2020, methodology): “Figure 2: One cycle of the evolutionary method [25, 69].”
AssembleNet: Searching for Multi-Stream Neural Connectivity in Video Architectures (2019, positive): “We use the tournament selection algorithm [10] as the main evolution framework: At each evolution round, the algorithm updates the population by selecting a ‘parent’ architecture and mutating (i.e., modifying) it to generate a new ‘child’ architecture.”
EENA: Efficient Evolution of Neural Architecture (2019, methodology): “Our evolutionary algorithm uses tournament selection (Goldberg and Deb, 1991) to select an individual for mutation: a fraction k of individuals is selected from the population randomly and the individual with highest fitness is final selected from this set.”
A Survey on Neural Architecture Search (2019, neutral): “The most common parent selection method in neural architecture search is tournament selection (Goldberg and Deb, 1990).”
Overcoming Multi-Model Forgetting (2019, background): “An example is the work of Liu et al. (2018a), who introduce a hierarchical representation of neural networks and use tournament selection (Goldberg & Deb, 1991) to evolve the architectures.”
NSGA-NET: A Multi-Objective Genetic Algorithm for Neural Architecture Search (2018, background): “A population of networks is maintained and are selected for mutation with tournament selection Goldberg & Deb (1991).”
Demystifying Parallel and Distributed Deep Learning (2018, methodology): “). However, in the general case GA requires synchronous reductive communication between time-steps for selection of the fittest candidates. To overcome this issue, the paper employstournamentselection[80], which only performs pairwise comparisons between population members. Additional GA architectur”
Evolving Reinforcement Learning Algorithms (2021, methodology): “For the outer loop optimization, we use regularized evolution (Real et al., 2019), a recent variant of classic evolutionary algorithms that employ tournament selection (Goldberg & Deb, 1991).”
Stochastic Optimization: a Review (2002, background): “Finally a third alternative is to usetournament selection (Goldberg & Deb, 1991).”
Evolutionary computation: a unified approach (2018, background): “For example, on polynomial and exponential landscapes the expected takeover time can be shown to be of order m ∗ log m (Goldberg and Deb, 1990).”
Genetic algorithms: theory, genetic operators, solutions, and applications (2023, unknown): “• Tournament selection [24]. s individuals are chosen randomly from the population.”
On the application of the microgenetic algorithm to the design of broad-band microwave absorbers comprising frequency-selective surfaces embedded in multilayered dielectric media (2001, background): “This selection was preferred because it converges more rapidly and it has a faster execution time than many other competing schemes [ 7 ].”
Machine Learning in Python: Main developments and technology trends in data science, machine learning, and artificial intelligence (2020, methodology): “Evolutionary computation was studied with the NASNet search space in AmoebaNet-A, where researchers at Google Brain proposed a novel approach to tournament selection [68].”
Evaluating the -Domination Based Multi-Objective Evolutionary Algorithm for a Quick Computation of Pareto-Optimal Solutions (2005, background): “In the context of single-objective EAs, it has been adequately shown that computational Evolutionary Computation Volume 13, Number 4 505 speed can be achieved by using a steady-state EA in which every offspring is compared with the parent population as soon as it is created (Goldberg and Deb, 1991).”
Evolutionary Compression of Deep Neural Networks for Biomedical Image Segmentation (2020, methodology): “In [44], a genetic algorithm (GA) [53] is adopted as a nongreedy strategy for compressing CNN.”
Symbolic Discovery of Optimization Algorithms (2023, background): “Each cycle picks T P algorithms at random and the best performer is chosen as the parent , i.e., tournament selection [32].”