Corpus ID: 18625190

On the Theoretical Capacity of Evolution Strategies to Statistically Learn the Landscape Hessian

@article{Shir2016OnTT,
  title={On the Theoretical Capacity of Evolution Strategies to Statistically Learn the Landscape Hessian},
  author={Ofer M. Shir and Jonathan Roslund and Amir Yehudayoff},
  journal={ArXiv},
  year={2016},
  volume={abs/1606.07262}
}
  • Ofer M. Shir, Jonathan Roslund, Amir Yehudayoff
  • Published 2016
  • Computer Science
  • ArXiv
  • We study the theoretical capacity to statistically learn local landscape information by Evolution Strategies (ESs). Specifically, we investigate the covariance matrix when constructed by 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… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 14 REFERENCES

    Completely Derandomized Self-Adaptation in Evolution Strategies

    VIEW 1 EXCERPT

    Evolution strategies – A comprehensive introduction

    VIEW 1 EXCERPT

    Stochastic Global Optimization

    VIEW 1 EXCERPT

    Contemporary Evolution Strategies. Natural Computing Series

    • T Bäck, C Foussette, P Krause
    • Contemporary Evolution Strategies. Natural Computing Series
    • 2013
    VIEW 1 EXCERPT