Corpus ID: 221516188

Convergence Analysis of the Hessian Estimation Evolution Strategy

@article{Glasmachers2020ConvergenceAO,
  title={Convergence Analysis of the Hessian Estimation Evolution Strategy},
  author={T. Glasmachers and O. Krause},
  journal={ArXiv},
  year={2020},
  volume={abs/2009.02732}
}
  • T. Glasmachers, O. Krause
  • Published 2020
  • Computer Science, Mathematics
  • ArXiv
  • The class of algorithms called Hessian Estimation Evolution Strategies (HEESs) update the covariance matrix of their sampling distribution by directly estimating the curvature of the objective function. The approach is practically efficient, as attested by respectable performance on the BBOB testbed, even on rather irregular functions. In this paper we formally prove two strong guarantees for the (1+4)-HE-ES, a minimal elitist member of the family: stability of the covariance matrix update, and… CONTINUE READING

    Figures from this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 25 REFERENCES
    The BOBYQA algorithm for bound constrained optimization without derivatives
    • 814
    • Highly Influential
    • PDF
    Completely Derandomized Self-Adaptation in Evolution Strategies
    • 2,917
    • Highly Influential
    • PDF
    Exponential natural evolution strategies
    • 138
    • PDF
    Natural Evolution Strategies
    • 435
    • PDF
    The Hessian Estimation Evolution Strategy
    • 1
    • PDF
    Covariance Matrix Adaptation for Multi-objective Optimization
    • 631
    • PDF
    Convergence results for the ( 1 , )-SA-ES using the theory of-irreducible Markov chains
    • 92
    • PDF
    How the (1+1) ES using isotropic mutations minimizes positive definite quadratic forms
    • 54
    • Highly Influential
    Information-Geometric Optimization Algorithms: A Unifying Picture via Invariance Principles
    • 125
    • PDF
    Simplify Your Covariance Matrix Adaptation Evolution Strategy
    • 36
    • PDF