On the theoretical capacity of evolution strategies to statistically learn the landscape

Ofer M. Shir, Jonathan Roslund, Amir Yehudayoff

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

We investigate the covariance matrix when constructed by Evolution Strategies (ESs) operating with the selection operator alone. We model continuous generation of candidate solutions about quadratic basins of attraction, with deterministic selection of the decision vectors that minimize the objective function values. Our goal is to rigorously show that accumulation of winning individuals carries the potential to reveal valuable information about the search landscape. We first show that the statistically-constructed covariance matrix over such winning decision vectors shares the same eigenvectors with the Hessian matrix about the optimum. We then provide an analytic approximation of this covariance matrix for a non-elitist multi-child (1,λ)-strategy, which holds for a large population size λ.

Original languageEnglish
Title of host publicationGECCO 2016 Companion - Proceedings of the 2016 Genetic and Evolutionary Computation Conference
EditorsTobias Friedrich
Pages151-152
Number of pages2
ISBN (Electronic)9781450343237
DOIs
StatePublished - 20 Jul 2016
Event2016 Genetic and Evolutionary Computation Conference, GECCO 2016 Companion - Denver, United States
Duration: 20 Jul 201624 Jul 2016

Publication series

NameGECCO 2016 Companion - Proceedings of the 2016 Genetic and Evolutionary Computation Conference

Conference

Conference2016 Genetic and Evolutionary Computation Conference, GECCO 2016 Companion
Country/TerritoryUnited States
CityDenver
Period20/07/1624/07/16

Keywords

  • Covariance matrix adaptation
  • Extreme value distributions
  • Landscape hessian
  • Limit distributions of order statistics
  • Statistical learning
  • Theory of evolution strategies

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Science Applications
  • Computational Theory and Mathematics

Cite this