A computational efficient covariance matrix update and a (1+1)-CMA for evolution strategies

First, the covariance matrix adaptation (CMA) with rankone update is introduced into the (1+1)-evolution strategy. An improved implementation of the 1/5-th success rule is proposed for step size adaptation, which replaces cumulative path length control. Second, an incremental Cholesky update for the covariance matrix is developed replacing the computational demanding and numerically involved decomposition of the covariance matrix. The Cholesky update can replace the decomposition only for the update without evolution path and reduces the computational effort from O(n3 ) to O(n2 ). The resulting (1+1)-Cholesky-CMA-ES is an elegant algorithm and the perhaps simplest evolution strategy with covariance matrix and step size adaptation. Simulations compare the introduced algorithms to previously published CMA versions. Categories and Subject Descriptors F.2.1 [Numerical Algorithms and Problems]: Compu

• Type: Conference
• Year: 2006
• Where: GECCO
• Authors: Christian Igel, Thorsten Suttorp, Nikolaus Hansen
• Keywords: Covariance Matrix, Covariance Matrix Adaptation, GECCO 2006, Optimization, Step Size Adaptation