The DOI matches its Crossref record; 40 of the 41 references it cites were found in a registry or an index.
Completely Derandomized Self-Adaptation in Evolution Strategies
Abstract
This paper puts forward two useful methods for self-adaptation of the mutation distribution - the concepts of derandomization and cumulation. Principle shortcomings of the concept of mutative strategy parameter control and two levels of derandomization are reviewed. Basic demands on the self-adaptation of arbitrary (normal) mutation distributions are developed. Applying arbitrary, normal mutation distributions is equivalent to applying a general, linear problem encoding. The underlying objective of mutative strategy parameter control is roughly to favor previously selected mutation steps in the future. If this objective is pursued rigorously, a completely derandomized self-adaptation scheme results, which adapts arbitrary normal mutation distributions. This scheme, called covariance matrix adaptation (CMA), meets the previously stated demands. It can still be considerably improved by cumulation - utilizing an evolution path rather than single search steps. Simulations on various test functions reveal local and global search properties of the evolution strategy with and without covariance matrix adaptation. Their performances are comparable only on perfectly scaled functions. On badly scaled, non-separable functions usually a speed up factor of several orders of magnitude is observed. On moderately mis-scaled functions a speed up factor of three to ten can be expected.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Due to its well-known robustness to local minima, the CMAES benchmark method”
From A Fully Differentiable Framework for 2D/3D Registration and the Projective Spatial Transformers (2024) · cites this paper as [40]
Citations
Cites
Numerical recipes in Pascal: the art of scientific computing
(1990) · Choice Reviews Online · doi:10.5860/choice.27-5158 · Cited by 12,040
Evolutionsstrategie : Optimierung technischer Systeme nach Prinzipien der biologischen Evolution
Rechenberg, I. (1973) · Frommann-Holzboog eBooks · Cited by 2,440
Schwefel, H. (1995) · Cited by 2,203
An Overview of Evolutionary Algorithms for Parameter Optimization
Bäck, T., & Schwefel, H. (1993) · Evolutionary Computation · doi:10.1162/evco.1993.1.1.1 · Cited by 2,111
Numerical optimization of computer models
(1982) · Mathematics and Computers in Simulation · doi:10.1016/0378-4754(82)90117-3 · Cited by 1,626
Evolutionary computation: Comments on the history and current state
Back, T., Hammel, U., & Schwefel, H.-P. (1997) · IEEE Transactions on Evolutionary Computation · doi:10.1109/4235.585888 · Cited by 1,536 · cited 1×
“It is generally recognized that the typical values for μ = 15 and λ = 100 are not sufficient for this adaptation mechanism (Bäck et al., 1997).”
BackgroundHansen, N., & Ostermeier, A. (2002) · IEEE Congress on Evolutionary Computation (CEC) · doi:10.1109/icec.1996.542381 · Cited by 1,110
Self-citation(2000) · Institute of Physics eBooks · doi:10.1887/0750306645 · Cited by 765
A framework for evolutionary optimization with approximate fitness functions
Jin, Y., Olhofer, M., & Sendhoff, B. (2002) · IEEE Transactions on Evolutionary Computation · doi:10.1109/tevc.2002.800884 · Cited by 663
Evolution and Optimum Seeking: The Sixth Generation
Schwefel, H. (1993) · John Wiley & Sons, Inc. eBooks · Cited by 652
Research works printed but not linked: 2
- Cerveri P., 2001, IEEE Transactions on Evolutionary Computation, in press.
- Olhofer M., 2000, Parmee, I., editor, Adaptive Computing in Design and Manufacture (ACDM), pages, 45
Cited by
Sorted by citations
Deep learning in neural networks: an overview
Schmidhuber, J. (2015) · Neural Networks · doi:10.1016/j.neunet.2014.09.003 · Cited by 18,570
Larian Studios Dev Team (2024) · doi:10.1145/3292500.3330701 · Cited by 8,618
“This way, the framework can identify the underlying concurrence relations after some number of independent samplings, and use the inferred concurrence relation to conduct user-selected relational sampling algorithms like CMA-ES [17] and GP-BO [18].”
MethodTaking the Human Out of the Loop: A Review of Bayesian Optimization
Shahriari, B., Swersky, K., Wang, Z., Adams, R. P., & de Freitas, N. (2015) · Proceedings of the IEEE · doi:10.1109/jproc.2015.2494218 · Cited by 6,195
Differential Evolution: A Survey of the State-of-the-Art
Das, S., & Suganthan, P. N. (2011) · IEEE Transactions on Evolutionary Computation · doi:10.1109/tevc.2010.2059031 · Cited by 5,307
Evolution strategies – A comprehensive introduction
Beyer, H.-G., & Schwefel, H. (2002) · Natural Computing · doi:10.1023/a:1015059928466 · Cited by 2,810
Metadata
- Authors
- Hansen, N., & Ostermeier, A.
- Affiliations
- Technische Universität Berlin (DE)
- ORCID
- Hansen, Nikolaus
- Venue
- Evolutionary Computation
- Publisher
- MIT Press
- Published
- 2001-06
- Volume
- 9
- Issue
- 2
- Pages
- 159-195
- ISSN
- 1063-6560 (ISSN-L)
- 1530-9304
- OpenAlex
- W2112036188
- Cited by
- 4,397
- References
- 41
- Citations by year
- 2026: 342 · 2025: 296 · 2024: 247 · 2023: 260 · 2022: 261 · 2021: 295 · 2020: 279 · 2019: 253 · 2018: 243 · 2017: 202 · 2016: 204 · 2015: 174 · 2014: 210 · 2013: 152 · 2012: 179
- FWCI
- 31.27
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Evolutionary Computation (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Metaheuristic Optimization Algorithms Research
- Physical Sciences › Computer Science › Artificial Intelligence › Evolutionary Algorithms and Applications
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Genetics › Evolution and Genetic Dynamics
- Keywords
- evolution strategies, self-adaptation, derandomization, covariance matrix adaptation, mutation distribution, cumulation, evolution path, global and local search
- MeSH terms
- Algorithms, Computer Simulation, Biological Evolution, Models, Genetic, Mutation, Stochastic Processes, Models, Statistical
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
