PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Comparison-based algorithms are robust and randomized algorithms are anytime
Olivier Teytaud, Sylvie Ruette and Sylvain Gelly
Evolutionary Computation Journal Volume 15, Number 4, 2007.

Abstract

Randomized search heuristics (e.g., evolutionary algorithms, simulated annealing etc.) are very appealing to practitioners, they are easy to implement and usually provide good performance. The theoretical analysis of these algorithms usually focuses on convergence rates. This paper presents a mathematical study of randomized search heuristics which use comparison based selection mechanism. The two main results are: (i) comparison-based algorithms are the best algorithms for some robustness criteria, (ii) introducing randomness in the choice of offspring improves the anytime behavior of the algorithm. An original Estimation of Distribution Algorithm combining (i) and (ii) is proposed and successfully experimented.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Learning/Statistics & Optimisation
ID Code:3199
Deposited By:Olivier Teytaud
Deposited On:20 January 2008