The CMA Evolution Strategy: A Tutorial

Nikolaus Hansen (1)

1 TAO - Machine Learning and Optimisation

This tutorial introduces the CMA Evolution Strategy (ES), where CMA stands for Covariance Matrix Adaptation. The CMA-ES is a stochastic, or randomized, method for real-parameter (continuous domain) optimization of non-linear, non-convex functions. We try to motivate and derive the algorithm from intuitive concepts and from requirements of non-linear, non-convex search in continuous domain.

Mots clés: numerical optimization; evolution strategies; covariance matrix adaptation; CMA-ES; CMA

Domaines: Apprentissage [cs.LG]

Nikolaus Hansen. The CMA Evolution Strategy: A Tutorial. 2005. ⟨hal-01297037v2⟩