Convergence rates for Markov chains
SIAM Review
Evolutionary algorithms in theory and practice: evolution strategies, evolutionary programming, genetic algorithms
Exact sampling with coupled Markov chains and applications to statistical mechanics
Proceedings of the seventh international conference on Random structures and algorithms
Genetic programming: an introduction: on the automatic evolution of computer programs and its applications
The evolution of size and shape
Advances in genetic programming
Sub-machine-code genetic programming
Advances in genetic programming
Foundations of genetic programming
Foundations of genetic programming
Genetic Programming and Data Structures: Genetic Programming + Data Structures = Automatic Programming!
SIAM Review
Review: Discipulus: A Commercial Genetic Programming System
Genetic Programming and Evolvable Machines
Convergence Rates For The Distribution Of Program Outputs
GECCO '02 Proceedings of the Genetic and Evolutionary Computation Conference
Evolving Hand-Eye Coordination for a Humanoid Robot with Machine Code Genetic Programming
EuroGP '01 Proceedings of the 4th European Conference on Genetic Programming
Using Reversible Computing To Achieve Fail-Safety
ISSRE '97 Proceedings of the Eighth International Symposium on Software Reliability Engineering
Rigorous hitting times for binary mutations
Evolutionary Computation
Mapping non-conventional extensions of genetic programming
UC'06 Proceedings of the 5th international conference on Unconventional Computation
No free lunch theorems for optimization
IEEE Transactions on Evolutionary Computation
Hi-index | 0.00 |
The distribution of fitness values (landscapes) of programs tends to a limit as the programs get bigger. We use Markov chain convergence theorems to give general upper bounds on the length of programs needed for convergence. How big programs need to be to approach the limit depends on the type of the computer they run on. We give bounds (exponential in N, N log N and smaller) for five computer models: any, average or amorphous or random, cyclic, bit flip and four functions (AND, NAND, OR and NOR). Programs can be treated as lookup tables which map between their inputs and their outputs. Using this we prove similar convergence results for the distribution of functions implemented by linear computer programs. We show most functions are constants and the remainder are mostly parsimonious. The effect of ad-hoc rules on genetic programming (GP) are described and new heuristics are proposed. We give bounds on how long programs need to be before the distribution of their functionality is close to its limiting distribution, both in general and for average computers. The computational importance of destroying information is discussed with respect to reversible and quantum computers. Mutation randomizes a genetic algorithm population in $$\frac{1}{4}(l+1)(\hbox{log}\,(l)+4)$$ generations. Results for average computers and a model like genetic programming are confirmed experimentally.