Toward a Theory of Evolution Strategies: The (μ, λ)-Theory-Reference-Cited by-同舟云学术

Toward a Theory of Evolution Strategies: The (μ, λ)-Theory

Published:1994-12 Issue:4 Volume:2 Page:381-407
ISSN:1063-6560
Container-title:Evolutionary Computation
language:en
Short-container-title:Evolutionary Computation

Author:

Beyer Hans-Georg¹

Affiliation:

1. University of Dortmund, Department of Computer Science, Systems Analysis Research Group, D-44221 Dortmund, Germany

Abstract

The multimembered evolution strategy (ES) acting on μ parents and λ offspring is analyzed for real-valued, N-dimensional parameter spaces (N ≳ 30). N-dependent progress rate formulas are derived for (1, λ) and (μ, λ) strategies on spherical models. The analytical results obtained are compared with simulation experiments for the (hyper)sphere and the inclined (hyper)plane.

Publisher

MIT Press - Journals

Subject

Computational Mathematics

Link

https://www.mitpressjournals.org/doi/pdf/10.1162/evco.1994.2.4.381

Reference1 articles.

Cited by 60 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Deep Learning Evolved: Overcoming Sub-Optimal Local Minima with $(\mu/\rho+\lambda)$–Evolution Strategies;2023 Congress in Computer Science, Computer Engineering, & Applied Computing (CSCE);2023-07-24

2. A Survey and Tutorial on Network Optimization for Intelligent Transport System Using the Internet of Vehicles;Sensors;2023-01-03

3. Finding the Optimal Network Topology for the Distributed Multi-Short-Paths Routing Algorithm — A Genetic Algorithm-Based Approach;2022 International Conference on Intelligent Systems and Computational Intelligence (ICISCI);2022-10-15

4. Multipopulation-based multi-tasking evolutionary algorithm;Applied Intelligence;2022-06-13

5. An Evaluation of a Bootstrapped Neuro-Evolution Approach;Conference of the South African Institute of Computer Scientists and Information Technologists 2020;2020-09-11