EAs-from-the-papers

Evolutionary algorithms from the papers

Content

1. Analysis & Convergence Analysis

2. Classical Evolution Strategies

3. CMA-ES & Its Variants

4. Natural Evolution Strategies

5. Differential Evolution & Its Variants

6. Information Geometry & Information Geometric Optimization

Analysis & Convergence Analysis

1. Natural Evolution Strategies Converge on Sphere Functions. GECCO '12. [paper, reference]

   Tom Schaul.

2. Learning Rate Adaptation by Line Search in Evolution Strategies with Recombination. GECCO '22. [paper, appendix, reference]

   Armand Gissler, Anne Auger, Nikolaus Hansen.

3. Analysis of Evolution Strategies with the Optimal Weighted Recombination. GECCO '18. [paper, reference]

   Chun-kit Au, Ho-fung Leung.

4. Analysis of Information Geometric Optimization with Isotropic Gaussian Distribution Under Finite Samples. GECCO '18. [paper, reference]

   Kento Uchida, Shinichi Shirakawa, Youhei Akimoto.

5. Reconsidering the Progress Rate Theory for Evolution Strategies in Finite Dimensions. GECCO '06. [paper, reference]

   Anne Auger, Nikolaus Hansen.

6. Convergence Rates of Efficient Global Optimization Algorithms. JMLR vol. 12, 2011. [paper, reference]

   Adam D. Bull.

7. Towards a Stronger Theory for Permutation-based Evolutionary Algorithms. GECCO '22. [paper, reference]

   Benjamin Doerr, Yassine Ghannane, Marouane Ibn Brahim.

8. Convergence Rate of the (1+1)-Evolution Strategy with Success-Based Step-Size Adaptation on Convex Quadratic Functions. GECCO '21. [paper, reference]

   Daiki Morinaga, Kazuto Fukuchi, Jun Sakuma, Youhei Akimoto.

9. Simple algorithms for optimization on Riemannian manifolds with constraints. Applied Mathematics & Optimization, vol. 82, 2020. [paper, reference]

   Changshuo Liu, Nicolas Boumal.

10. Globally convergent evolution strategies. Mathematical Programming, vol. 152. [paper, reference]

    Y. Diouane, S. Gratton, L. N. Vicente.

11. On Proving Linear Convergence of Comparison-based Step-size Adaptive Randomized Search on Scaling-Invariant Functions via Stability of Markov Chains. INRIA, 2013. [paper, reference]

    Anne Auger, Nikolaus Hansen.

12. Convergence Analysis of Optimization Algorithms. arXiv. [paper, reference]

    HyoungSeok Kim, JiHoon Kang, WooMyoung Park, SukHyun Ko, YoonHo Cho, DaeSung Yu, YoungSook Song and JungWon Choi.

13. Convergence Analysis. Lecture. [document]

14. Numerical Optimization. Class note. [document]

15. The Benefits and Limitations of Voting Mechanisms in Evolutionary Optimisation. FOGA '19. [paper, reference]

    Jonathan E. Rowe, Aishwaryaprajna.

16. Convergence Analysis of Differential Evolution Variants on Unconstrained Global Optimization Functions. IJAIA, vol. 2, 2011. [paper, reference]

    G.Jeyakumar, C.Shanmugavelayutham.

Classical Evolution Strategies

1. The Dynamics of Cumulative Step-Size Adaptation on the Ellipsoid Model. Evolutionary Computation, vol. 24, 2016. [paper, reference]

   Hans-Georg Beyer, Michael Hellwig.

2. Global linear convergence of Evolution Strategies with recombination on scaling-invariant functions. Journal of Global Optimization, vol. 86, 2023. [paper, reference]

   Cheikh Toure, Anne Auger, Nikolaus Hansen.

3. Log-linear Convergence of the Scale-invariant (µ/µw, λ)-ES and Optimal µ for Intermediate Recombination for Large Population Sizes. PPSN '10. [paper, reference]

   Mohamed Jebalia, Anne Auger.

4. On a Population Sizing Model for Evolution Strategies Optimizing the Highly Multimodal Rastrigin Function. GECCO '23. [paper, reference]

   Lisa Schönenberger, Hans-Georg Beyer.

5. Self-Adaptation of Multi-Recombinant Evolution Strategies on the Highly Multimodal Rastrigin Function. Evolutionary Compatation, 2024. [paper, reference]

   Amir Omeradzic, Hans-Georg Beyer.

6. The Dynamics of Self-Adaptive Multi-Recombinant Evolution Strategies on the General Ellipsoid Model. Evolutionary Computation, vol. 18, 2014. [paper, reference]

   Hans-Georg Beyer, Alexander Melkozerov.

7. Self-Adaptation in Evolution Strategies. Thesis. [document, reference]

   Silja Meyer-Nieberg.

8. The Theory of Evolution Strategies. Book. [document, reference]

   Hans-Georg Beyer.

9. Markov chain Analysis of Evolution Strategies. Thesis. [document, reference]

   Alexandre Chotard.

10. Bias in Standard Self-Adaptive Evolution Strategies. CEC, 2024. [paper, reference]

    Amir Omeradzic, Hans-Georg Beyer.

CMA-ES & Its Variants

1. The CMA Evolution Strategy: A Tutorial. arXiv. [paper, reference]

   Nikolaus Hansen.

2. Completely Derandomized Self-Adaptation in Evolution Strategies. Evolutionary Computation, vol. 9, 2001. [paper, reference]

   Nikolaus Hansen, Andreas Ostermeier.

3. A Restart CMA Evolution Strategy With Increasing Population Size. CEC, 2005. [paper, reference]

   Anne Auger, Nikolaus Hansen.

4. Deriving and Improving CMA-ES with Information Geometric Trust Regions. GECCO '17. [paper, reference]

   Abbas Abdolmaleki, Bob Price, Nuno Lau, Luis Paulo Reis, Gerhard Neumann.

5. Theoretical Foundation for CMA-ES from Information Geometry Perspective. arXiv. [paper, reference]

   Youhei Akimoto, Yuichi Nagata, Isao Ono, Shigenobu Kobayashi.

6. A Derandomized Approach to Self Adaptation of Evolution Strategies. Evolutionary Computation, vol. 2, 1994. [paper, reference]

   Andreas Ostermeier, Andreas Gawelczyk, Nikolaus Hansen.

7. Simplify Your Covariance Matrix Adaptation Evolution Strategy. Evolutionary Computation, vol. 21, 2017. [paper, reference]

   Hans-Georg Beyer, Bernhard Sendhoff.

8. Sample Reuse in the Covariance Matrix Adaptation Evolution Strategy Based on Importance Sampling. GECCO '15. [paper, reference]

   Shinichi Shirakawa, Youhei Akimoto, Kazuki Ouchi, Kouzou Ohara.

9. CMA-ES with Learning Rate Adaptation: Can CMA-ES with Default Population Size Solve Multimodal and Noisy Problems?. GECCO '23. [paper, reference]

   Masahiro Nomura, Youhei Akimoto, Isao Ono.

Natural Evolution Strategies

1. Natural Evolution Strategies. JMLR, vol. 15, 2014. [paper, reference]

   Daan Wierstra, Tom Schaul, Tobias Glasmachers, Yi Sun, Jan Peters, Jürgen Schmidhuber.

2. Exponential Natural Evolution Strategies. GECCO '10. [paper, reference]

   Tobias Glasmachers, Tom Schaul, Sun Yi, Daan Wierstra, Jürgen Schmidhuber.

3. Efficient Natural Evolution Strategies. GECCO '09. [paper, reference]

   Yi Sun, Daan Wierstra, Tom Schaul, Jürgen Schmidhuber.

4. Bidirectional Relation between CMA Evolution Strategies and Natural Evolution Strategies. PPSN '10. [paper, reference]

   Youhei Akimoto, Yuichi Nagata, Isao Ono, Shigenobu Kobayashi.

5. High Dimensions and Heavy Tails for Natural Evolution Strategies. GECCO '11. [paper, reference]

   Tom Schaul, Tobias Glasmachers, Jürgen Schmidhuber.

Differential Evolution & Its Variants

1. Modular Differential Evolution. GECCO '23. [paper, reference]

   Diederick Vermetten, Fabio Caraffini, Anna V. Kononova, Thomas Bäck.

2. Geometric Differential Evolution. GECCO '09. [paper, reference]

   Alberto Moraglio, Julian Togelius.

3. Success-History Based Parameter Adaptation for Differential Evolution. CEC, 2013. [paper, reference]

   Ryoji Tanabe, Alex Fukunaga.

4. Differential Evolution Algorithm With Strategy Adaptation for Global Numerical Optimization. Evolutionary Computation, vol. 13, 2009. [paper, reference]

   A. K. Qin, V. L. Huang, and P. N. Suganthan.

5. A Novel Similarity-based Mutant Vector Generation Strategy for Differential Evolution. GECCO '18. [paper, reference]

   Eduardo Segredo, Eduardo Lalla-Ruiz, Emma Hart.

6. Differential Evolution with Composite Trial Vector Generation Strategies and Control Parameters. Evolutionary Computation, vol. 15, 2011. [paper, reference]

   Yong Wang, Zixing Cai, Qingfu Zhang.

Information Geometry & Information Geometric Optimization

1. Why Natural Gradient?. ICASSP, 1998. [paper, reference]

   S. Amari, S.C. Douglas.

2. Information Geometry of the Gaussian Distribution in View of Stochastic Optimization. FOGA '15. [paper, reference]

   Luigi Malagò, Giovanni Pistone.

3. Information-Geometric Optimization Algorithms: A Unifying Picture via Invariance Principles. JMLR, vol. 18, 2017. [paper, reference]

   Yann Ollivier, Ludovic Arnold, Anne Auger, Nikolaus Hansen.

4. Convergence Analysis of Evolutionary Algorithms That are Based on the Paradigm of Information Geometry. Evolutionary Computation, vol. 28, 2014. [paper, reference]

   Hans-Georg Beyer.

5. Information Geometry and Its Applications. Lecture. [document]

   S. Amari.

6. Information Geometry and Its Applications to Machine Learning. Lecture. [document]

   S. Amari.

7. Information Geometry and Its Applications. Lecture. [document]

   S. Amari.