PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

DCMA, yet another derandomization in covariance matrix adaptation
Olivier Teytaud and Justin Bedo
In: Gecco 2007, 2007, London.


In a preliminary part of this paper, we analyze the neces- sity of randomness in evolution strategies. We conclude to the necessity of ”continuous”-randomness, but with a much more limited use of randomness than what is commonly used in evolution strategies. We then apply these results to CMA- ES, a famous evolution strategy already based on the idea of derandomization, which uses random independent Gaus- sian mutations. We here replace these random independent Gaussian mutations by a quasi-random sample. The mod- ification is very easy to do, the modified algorithm is com- putationally more efficient and its convergence is faster in terms of the number of iterates for a given precision.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Learning/Statistics & Optimisation
ID Code:3197
Deposited By:Olivier Teytaud
Deposited On:20 January 2008