Supervisors:
Anne Auger,
Nikolaus Hansen
Context
Evolution strategies are search or optimization methods that search for good solutions in continuous domain search spaces, where good is defined by a given fitness function. Originally inspired by biological evolution more than forty years ago, evolution strategies have matured and become competitive and comparatively well-understood. The
covariance matrix adaptation evolution strategy (CMA-ES) is a modern variant that samples new solutions from a multivariate normal distribution adapting variances and covariances of this distribution. Many interesting interpretations and justifications of the CMA-ES have been proposed and most recently, it has been shown to conduct a
natural gradient descent in the distribution space (as opposed to the search space). We propose several topics connected the CMA-ES.