ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2006.04663
10
5
v1v2v3 (latest)

Runtime Analysis of Evolutionary Algorithms via Symmetry Arguments

8 June 2020
Benjamin Doerr
    LRM
ArXiv (abs)PDFHTML
Abstract

We use an elementary argument building on group actions to prove that the selection-free steady state genetic algorithm analyzed by Sutton and Witt (GECCO 2019) takes an expected number of Ω(2n/n)\Omega(2^n / \sqrt n)Ω(2n/n​) iterations to find any particular target search point. This bound is valid for all population sizes μ\muμ. Our result improves over the previous lower bound of Ω(exp⁡(nδ/2))\Omega(\exp(n^{\delta/2}))Ω(exp(nδ/2)) valid for population sizes μ=O(n1/2−δ)\mu = O(n^{1/2 - \delta})μ=O(n1/2−δ), 0<δ<1/20 < \delta < 1/20<δ<1/2.

View on arXiv
Comments on this paper