A Discipline of Evolutionary Programming

@article{Vitnyi2000ADO,
  title={A Discipline of Evolutionary Programming},
  author={Paul M. B. Vit{\'a}nyi},
  journal={Theor. Comput. Sci.},
  year={2000},
  volume={241},
  pages={3-23}
}
Genetic fitness optimization using small populations or small population updates across generations generally suffers from randomly diverging evolutions. We propose a notion of highly probable fitness optimization through feasible evolutionary computing runs on small size populations. Based on rapidly mixing Markov chains, the approach pertains to most types of evolutionary genetic algorithms, genetic programming and the like. We establish that for systems having associated rapidly mixing… CONTINUE READING