# Hyperparameter Tuning in Echo State Networks

arXiv: https://arxiv.org/abs/2207.07976 · HTML: https://mlsanity.com/paper/2207.07976/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Jul 2022.

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

- [A Random Matrix Perspective of Echo State Networks: From Precise Bias--Variance Characterization to Optimal Regularization](https://mlsanity.com/paper/2509.22011/) (2025)
- [Free-Probability Kernels for Zero-Rollout Hyperparameter Selection in Reservoir Computing](https://mlsanity.com/paper/2608.20998/) (2026)

## Abstract (arXiv)

Echo State Networks represent a type of recurrent neural network with a large randomly generated reservoir and a small number of readout connections trained via linear regression. The most common topology of the reservoir is a fully connected network of up to thousands of neurons. Over the years, researchers have introduced a variety of alternative reservoir topologies, such as a circular network or a linear path of connections. When comparing the performance of different topologies or other architectural changes, it is necessary to tune the hyperparameters for each of the topologies separately since their properties may significantly differ. The hyperparameter tuning is usually carried out manually by selecting the best performing set of parameters from a sparse grid of predefined combinations. Unfortunately, this approach may lead to underperforming configurations, especially for sensitive topologies. We propose an alternative approach of hyperparameter tuning based on the Covariance Matrix Adaptation Evolution Strategy (CMA-ES). Using this approach, we have improved multiple topology comparison results by orders of magnitude suggesting that topology alone does not play as important role as properly tuned hyperparameters.