# Improving Evolutionary Strategies with Generative Neural Networks

arXiv: https://arxiv.org/abs/1901.11271 · HTML: https://mlsanity.com/paper/1901.11271/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Jan 2019.

## Built on by (most cited first, 2 of 2)

- [Inverse Design of Grating Couplers Using the Policy Gradient Method from Reinforcement Learning](https://mlsanity.com/paper/2107.00088/) (2021)
- [OPT-GAN: A Broad-Spectrum Global Optimizer for Black-box Problems by Learning Distribution](https://mlsanity.com/paper/2102.03888/) (2021)

## Abstract (arXiv)

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 classical ES algorithms, in contrast to standard ones (typically Gaussians). We model such distributions with Generative Neural Networks (GNNs) and introduce a new training algorithm that leverages their expressiveness to accelerate the ES procedure. We show that this tailored algorithm can readily incorporate existing ES algorithms, and outperforms the state-of-the-art on diverse objective functions.