Toward a steady-state analysis of an evolution strategy on a robust optimization problem with noise-induced multimodality

HG Beyer, B Sendhoff - IEEE Transactions on Evolutionary …, 2017 - ieeexplore.ieee.org
A steady state analysis of the optimization quality of a classical self-adaptive evolution
strategy (ES) on a class of robust optimization problems is presented. A novel technique for …

The dynamics of cumulative step size adaptation on the ellipsoid model

HG Beyer, M Hellwig - Evolutionary computation, 2016 - direct.mit.edu
The behavior of the-Evolution Strategy (ES) with cumulative step size adaptation (CSA) on
the ellipsoid model is investigated using dynamic systems analysis. At first a nonlinear …

Comparison of constraint-handling mechanisms for the (1, λ)-ES on a simple constrained problem

M Hellwig, DV Arnold - Evolutionary Computation, 2016 - ieeexplore.ieee.org
This paper investigates constraint-handling techniques used in nonelitist single-parent
evolution strategies for the problem of maximizing a linear function with a single linear …

[HTML][HTML] Mutation strength control via meta evolution strategies on the ellipsoid model

M Hellwig, HG Beyer - Theoretical Computer Science, 2016 - Elsevier
The ability of a hierarchically organized evolution strategy (meta evolution strategy) with
isolation periods of length one to optimally control its mutation strength is investigated on …

On the behaviour of the (1, λ)-ES for conically constrained linear problems

DV Arnold - Evolutionary Computation, 2014 - ieeexplore.ieee.org
We study the behaviour of a (1, λ)-ES that handles constraints by resampling infeasible
candidate solutions for linear optimization problems with a conically constrained feasible …

Finite-sample analysis of information geometric optimization with isotropic Gaussian distribution on convex quadratic functions

K Uchida, S Shirakawa… - IEEE Transactions on …, 2019 - ieeexplore.ieee.org
We theoretically analyze the information geometric optimization (IGO), which is a unified
framework of stochastic search algorithms for black-box optimization. The IGO framework …

Analysis of a meta-ES on a conically constrained problem

M Hellwig, HG Beyer - Proceedings of the Genetic and Evolutionary …, 2019 - dl.acm.org
The paper presents the theoretical performance analysis of a hierarchical Evolution Strategy
(meta-ES) variant for mutation strength control on a conically constrained problem …

Analysis of information geometric optimization with isotropic Gaussian distribution under finite samples

K Uchida, S Shirakawa, Y Akimoto - Proceedings of the Genetic and …, 2018 - dl.acm.org
In this article, we theoretically investigate the convergence properties of the information
geometric optimization (IGO) algorithm given the family of isotropic Gaussian distributions on …

Analyzing the behaviour of multi-recombinative evolution strategies applied to a conically constrained problem

J Porter, DV Arnold - Evolutionary Constrained Optimization, 2015 - Springer
Many step size adaptation techniques for evolution strategies have been developed with
unconstrained optimization problems in mind. In constrained settings, the interplay between …

Guest Editorial Special Issue on Theoretical Foundations of Evolutionary Computation

PS Oliveto, A Auger, F Chicano… - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
It is our pleasure to introduce this special issue on the recent advances in the theoretical
foundations of evolutionary computation (EC). While in the early days of this field, theoretical …