This document presents an improved messy genetic algorithm (mGA) called fast messy GA (fmGA) that aims to optimize difficult problems more rapidly and accurately. It addresses the complexity issue of mGAs by introducing two key improvements: probabilistic initialization and building block filtering. Through experiments on concatenations of deceptive k-trap functions, the fmGA showed it could solve such problems with overall complexity of O(l log l), demonstrating faster processing than standard mGAs while maintaining their theoretical advantages.

1. Rapid Accurate Optimization of Difficult Problems Using Fast Messy Genetic Algorithms D.E. Goldberg, K. Deb, H. Kargupta & G. Harik, 1993 Presented by : Yann SEMET Visiting Student Universite de Technologie de Compiegne France

2. Roadmap & Foreword Framework & motivations Brief review of mGAs What ’s new ? Probabilistically Complete Initialization Building Block Filtering Thresholding revisited Experiments & Analysis Discussion

3. Framework & Motivations From simple GAs to fmGAs : Design of competent GAs Tackling hard,deceptive problems How : Taking care of the building blocks Messiness : mGAs Efficiency : fmGAs

4. Messy GAs ? mGAs are different from simple GAs : variable string length no fixed locus cut & splice Over and under specification Primordial and juxtapositional phases Inner, outer loops and k-wise processing

5. Complexity concerns 1 single copy of all k-substrings !

6. Toward Fast Processing Avoid the initialization Bottleneck partial enumeration = unGAlike ? Back to earlier unsuccessful ideas : probabilistic initialization shortening the strings 2 suggested improvements : probabilistically complete initialization and BB filtering.

7. Probabilistically Complete Initialization Random instead of explicit l’=l-k is a good choice Overall Cost : O(l)

8. Building Block Filtering Reducing string length down to k By performing alternatively : Selection alone Random deletion Don ’t delete mindlessly ! Key : more duplication than deletion

9. Building Block Filtering 2

10. Overall Complexity Initialization : O(l) BB filtering : O(log(l)) Overall :O(l.log(l)) Fits the remainder of the mGA! Goal achieved.

11. Thresholding revisited Restrict competition among too dissimilar BBs Genic Thresholding mechanism New values :

12. Experiments Concatenation of k-trap functions No mutation p(splice)=1 ; p(cut)=0.03 Competitive template : 000… l ’=l-k No k-wise processing

13. Base-Line results k=3 26650 function calls instead of 40600

14. Larger scale problems K=5 ; 10, 14 and 30 times 1.9*10^5 function calls for 150-bits !

15. Analysis & Strengths Winning heuristics Conservative assumptions No parameter fiddling Theoretical basis The long-short-long signature

16. Summary 1 problem : complexity 2 solutions : stochasticity and filtering 1 result : overall cost O(l.log(l)) Successful experiments

17. Conclusions Natural Fuzziness is good Yet, supports the Design Decomposition//BBs approach

18. Future Challenges 1 Other misleading factors : Mixed scale and size problems Crosstalk Massive multimodality

19. Future Challenges 2 Suggested Carry-ons : Floating point codes Classifier codes Permutation codes (OmeGA)

20. Discussion and Critique Close to the real world ? Deceptive functions and real problems Conservative assumptions The natural metaphor Messiness or decomposition ? The long-short-long signature