Deriving and improving CMA-ES with information geometric trust regions

Abstract

CMA-ES is one of the most popular stochastic search algorithms. It performs favourably in many tasks without the need of extensive parameter tuning. The algorithm has many beneficial properties, including automatic step-size adaptation, efficient covariance updates that incorporates the current samples as well as the evolution path and its invariance properties. Its update rules are composed of well established heuristics where the theoretical foundations of some of these rules are also well understood. In this paper we will fully derive all CMA-ES update rules within the framework of expectation-maximisation-based stochastic search algorithms using information-geometric trust regions. We show that the use of the trust region results in similar updates to CMA-ES for the <i>mean</i> and the <i>covariance</i> matrix while it allows for the derivation of an improved update rule for the step-size. Our new algorithm, Trust-Region Co-variance Matrix Adaptation Evolution Strategy (TR-CMA-ES) is fully derived from first order optimization principles and performs favourably in compare to standard CMA-ES algorithm.

DOI: 10.1145/3071178.3071252

4 Figures and Tables

Cite this paper

@inproceedings{Abdolmaleki2017DerivingAI, title={Deriving and improving CMA-ES with information geometric trust regions}, author={Abbas Abdolmaleki and Bob Price and Nuno Lau and Lu{\'i}s Paulo Reis and Gerhard Neumann}, booktitle={GECCO}, year={2017} }