PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

When does quasi-random work ?
Olivier Teytaud
In: PPSN 2010(2008).


Previous papers presented various ways for introducing quasi-random numbers or de- randomization in evolution strategies, with in some cases some spectacular claims on the fact that the proposed technique was always and for all criteria better than standard mu- tations. We here focus on the quasi-random trick and see to which extent this technique is efficient, by an in-depth analysis including convergence rates, local minima, plateaus, non- asymptotic behavior and noise. We conclude to the very stable, efficient and straightforward applicability of quasi-random numbers in continuous evolutionary algorithms.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Talk)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Learning/Statistics & Optimisation
ID Code:6883
Deposited By:Olivier Teytaud
Deposited On:09 April 2010