sign in
english version rss feed

inria-00000540, version 1

Local and global oder 3/2 convergence of a surrogate evolutionary algorithm

Anne Auger () 1, Marc Schoenauer () 1, Olivier Teytaud () 1

GECCO - genetic and evolutionary computation conference (2005) 857-864

Abstract: We prove a fast (better than superlinear) local convergence rate for an algorithm based on a quadratic approximation of the fitness function. An almost sure global convergence rate is proved for a corresponding memetic algorithm.

  • 1:  TAO (INRIA Futurs)
  • INRIA – CNRS : UMR8623 – Université Paris XI - Paris Sud
  • Domain : Mathematics/Optimization and Control
 
  • inria-00000540, version 1
  • oai:hal.inria.fr:inria-00000540
  • From: 
  • Submitted on: Monday, 31 October 2005 21:58:03
  • Updated on: Wednesday, 16 May 2007 15:23:39
all articles on CCSd database...
all articles on CCSd database...
all articles on CCSd database...
all articles on CCSd database...
all articles on CCSd database...
all articles on CCSd database...
all articles on CCSd database...
all articles on CCSd database...
all articles on CCSd database...
all articles on CCSd database...
all articles on CCSd database...
all articles on CCSd database...
all articles on CCSd database...
all articles on CCSd database...
all articles on CCSd database...
all articles on CCSd database...
all articles on CCSd database...
all articles on CCSd database...
all articles on CCSd database...
all articles on CCSd database...