Is there anisotropy in structural bias?

@article{Vermetten2021IsTA,
  title={Is there anisotropy in structural bias?},
  author={Diederick Vermetten and Anna V. Kononova and Fabio Caraffini and Hao Wang and Thomas Back},
  journal={Proceedings of the Genetic and Evolutionary Computation Conference Companion},
  year={2021}
}
Structural Bias (SB) is an important type of algorithmic deficiency within iterative optimisation heuristics. However, methods for detecting structural bias have not yet fully matured, and recent studies have uncovered many interesting questions. One of these is the question of how structural bias can be related to anisotropy. Intuitively, an algorithm that is not isotropic would be considered structurally biased. However, there have been cases where algorithms appear to only show SB in some… 
2 Citations

Figures and Tables from this paper

Emergence of structural bias in differential evolution
TLDR
This paper analyzes the emergence of structural bias for Differential Evolution (DE) configurations and, specifically, the effect of different mutation, crossover and correction strategies and concludes with recommendations of which configurations should be avoided in order to run DE unbiased.
IOHanalyzer: Detailed Performance Analyses for Iterative Optimization Heuristics
TLDR
Key advantages of IOHanalyzer over other performance analysis packages are its highly interactive design, which allows users to specify the performance measures, ranges, and granularity that are most useful for their experiments, and the possibility to analyze not only performance traces, but also the evolution of dynamic state parameters.

References

SHOWING 1-10 OF 45 REFERENCES
Can Compact Optimisation Algorithms Be Structurally Biased?
In the field of stochastic optimisation, the so-called structural bias constitutes an undesired behaviour of an algorithm that is unable to explore the search space to a uniform extent. In this
Infeasibility and structural bias in Differential Evolution
TLDR
This work investigates structural bias in popular variants of Differential Evolution (DE), and attempts to identify which algorithm features trigger its emergence, and focuses on the (often overlooked) constraint handling mechanism.
Structural bias in population-based algorithms
TLDR
A theorem concerning the dynamics of population variance in the case of real-valued search spaces and a 'flat' fitness landscape is state and proved, revealing how structural bias can arise and manifest as non-uniform clustering of the population over time.
Emergence of structural bias in differential evolution
TLDR
This paper analyzes the emergence of structural bias for Differential Evolution (DE) configurations and, specifically, the effect of different mutation, crossover and correction strategies and concludes with recommendations of which configurations should be avoided in order to run DE unbiased.
Can Single Solution Optimisation Methods Be Structurally Biased?
TLDR
This paper investigates whether optimisation methods with the population made up of one solution can suffer from structural bias just like their multisolution variants and shows such strategy is shown to control the emergence of structural bias in single solution methods.
Principled Design of Continuous Stochastic Search: From Theory to Practice
  • N. Hansen, A. Auger
  • Computer Science, Mathematics
    Theory and Principled Methods for the Design of Metaheuristics
  • 2014
We derive a stochastic search procedure for parameter optimization from two first principles: (1) imposing the least prior assumptions, namely by maximum entropy sampling, unbiasedness and
THE CONTROL OF THE FALSE DISCOVERY RATE IN MULTIPLE TESTING UNDER DEPENDENCY
Benjamini and Hochberg suggest that the false discovery rate may be the appropriate error rate to control in many applied multiple testing problems. A simple procedure was given there as an FDR
Re-sampled inheritance compact optimization
TLDR
Numerical results not only show that RI consistently enhances the performances of compact algorithms, but also shed some light on the effectiveness of different compact logics at handling problems at different dimensionalities.
Completely Derandomized Self-Adaptation in Evolution Strategies
TLDR
This paper puts forward two useful methods for self-adaptation of the mutation distribution - the concepts of derandomization and cumulation and reveals local and global search properties of the evolution strategy with and without covariance matrix adaptation.
The Exact and Asymptotic Distributions of Cramer-von Mises Statistics
It is shown that an asymptotically precise one-term correction to the asymptotic distribution function of the classical Cramйr-von Mises statistic approximates the exact distribution function
...
1
2
3
4
5
...