Improving Evolutionary Strategies with Generative Neural Networks

Louis Faury, Clément Calauzènes, Olivier Fercoq

Keywords: black-box optimization, evolutionary strategies, generative neural networks

TL;DR: We propose a new algorithm leveraging the expressiveness of Generative Neural Networks to improve Evolutionary Strategies algorithms.

Abstract: Evolutionary Strategies (ES) are a popular family of black-box zeroth-order optimization algorithms which rely on search distributions to efficiently optimize a large variety of objective functions. This paper investigates the potential benefits of using highly flexible search distributions in ES algorithms, in contrast to standard ones (typically Gaussians). We model such distributions with Generative Neural Networks (GNNs) and introduce a new ES algorithm that leverages their expressiveness to accelerate the stochastic search. Because it acts as a plug-in, our approach allows to augment virtually any standard ES algorithm with flexible search distributions. We demonstrate the empirical advantages of this method on a diversity of objective functions.

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/improving-evolutionary-strategies-with/code)