Hyperparameter Tuning in Echo State Networks

TL;DR

This paper introduces a CMA-ES based method for hyperparameter tuning in Echo State Networks, significantly improving topology comparison results and highlighting the importance of proper hyperparameter optimization.

Contribution

It presents a novel hyperparameter tuning approach using CMA-ES for Echo State Networks, enhancing performance across different reservoir topologies.

Findings

Hyperparameter tuning with CMA-ES outperforms manual tuning.

Proper hyperparameter optimization reduces the impact of topology differences.

Improved topology comparison results by orders of magnitude.

Abstract

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.