Lower Bounds for Evolution Strategies Using VC-Dimension

  • Authors:
  • Olivier Teytaud;Hervé Fournier

  • Affiliations:
  • TAO (Inria), LRI, UMR 8623 (CNRS - Univ. Paris-Sud) ,Bât 490, Univ. Paris-Sud, Orsay, France 91405;Laboratoire PRiSM, CNRS UMR 8144 and Univ. Versailles St-Quentin en Yvelines, Versailles, France 78035

  • Venue:
  • Proceedings of the 10th international conference on Parallel Problem Solving from Nature: PPSN X
  • Year:
  • 2008

Quantified Score

Hi-index 0.00

Visualization

Abstract

We derive lower bounds for comparison-based or selection-based algorithms, improving existing results in the continuous setting, and extending them to non-trivial results in the discrete case. This is achieved by considering the VC-dimension of the level sets of the fitness functions; results are then obtained through the use of Sauer's lemma. In the special case of optimization of the sphere function, improved lower bounds are obtained by bounding the possible number of sign conditions realized by some systems of equations.