## Crynodeb

At last year's GECCO a novel perspective for theoretical performance analysis of evolutionary algorithms and other randomised search heuristics was introduced that concentrates on the expected function value after a pre-defined number of steps, called budget. This is significantly different from the common perspective where the expected optimisation time is analysed. While there is a huge body of work and a large collection of tools for the analysis of the expected optimisation time the new fixed budget perspective introduces new analytical challenges. Here it is shown how results on the expected optimisation time that are strengthened by deviation bounds can be systematically turned into fixed budget results. We demonstrate our approach by considering the (1+1) EA on LeadingOnes and significantly improving previous results. We prove that deviating from the expected time by an additive term of ω(n^{3/2}) happens only with probability o(1). This is turned into tight bounds on the function value using the inverse function. We use three, increasingly strong or general approaches to proving the deviation bounds, namely via Chebyshev's inequality, via Chernoff bounds for geometric random variables, and via variable drift analysis.

Iaith wreiddiol | Saesneg |
---|---|

Teitl | GECCO '13: Proceedings of the 15th annual conference on Genetic and evolutionary computation |

Golygyddion | Christian Blum |

Cyhoeddwr | Association for Computing Machinery |

Tudalennau | 1581-1588 |

Nifer y tudalennau | 8 |

ISBN (Argraffiad) | 9781450319638 |

Dynodwyr Gwrthrych Digidol (DOIs) | |

Statws | Cyhoeddwyd - 06 Gorff 2013 |

Digwyddiad | GECCO 2013 - Genetic and Evolutionary Computation Conference - Amsterdam, Yr Iseldiroedd Hyd: 06 Gorff 2013 → 10 Gorff 2013 |

### Cynhadledd

Cynhadledd | GECCO 2013 - Genetic and Evolutionary Computation Conference |
---|---|

Gwlad/Tiriogaeth | Yr Iseldiroedd |

Dinas | Amsterdam |

Cyfnod | 06 Gorff 2013 → 10 Gorff 2013 |